Diogenes Sovereign Multi-Protocol AI Gateway & MCP Server

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Diogenes Sovereign Multi-Protocol AI Gateway & MCP Server": {
      "url": "https://diogenes-l402-gateway.corinth.workers.dev/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (107)

• verify_agent_command_safety read-only

  Evaluates untrusted agent prompts, bash commands, and tool arguments to block prompt injection, destructive shell commands, and private-key exfiltration. Use when screening a general shell command or user prompt before autonomous agent execution; for statically validating SQL database queries at the AST level, use validate_sql_query_ast instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'payload' ('action_type' defaults to 'bash_command'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.

  Parameters:

  • payload (required) — string — Raw command string, script snippet, or untrusted prompt to inspect for safety violations.
  • action_type — string — Execution context of the payload; defaults to 'bash_command' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• validate_sql_query_ast read-only

  Performs static AST syntax tree parsing on SQL statements to verify strictly read-only SELECT clauses and reject mutations, stacked queries, or comment bypasses. Use when verifying that an agent-authored SQL statement is strictly read-only before running it on a database; for screening non-SQL bash commands or general agent prompts, use verify_agent_command_safety instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'sql_statement' ('dialect' defaults to 'postgres'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • sql_statement (required) — string — SQL statement string to statically parse and audit for read-only SELECT compliance (e.g. 'SELECT id, email FROM users WHERE active = 1').
  • dialect — string — SQL dialect ruleset used for AST token inspection; defaults to 'postgres' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• execute_python_sandbox read-only

  Audits Python source code for forbidden syscalls (os, subprocess, socket, open, eval) inside an AST-governed WebAssembly sandbox with no host filesystem access. Use when executing LLM-generated Python snippets safely; for checking shell commands without executing code, use verify_agent_command_safety instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'python_script' ('timeout_profile' defaults to 'fast_1s'), supports '?demo=true' or MPP (250 sats), and returns HTTP 400 if invalid.

  Parameters:

  • python_script (required) — string — Python 3 source script to audit and execute strictly inside an isolated AST-governed, non-privileged WebAssembly sandbox with no host filesystem access.
  • timeout_profile — string — Execution resource ceiling; defaults to 'standard_5s' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• audit_mcp_server_manifest read-only

  Scans an external MCP server's initial tools/list manifest to detect tool-name shadowing (read_file, bash) and hidden prompt-injection directives in descriptions. Use when vetting a newly discovered third-party MCP server before mounting it into an agent session; for comparing a previously pinned MCP baseline against a live mid-session tools/list response, use detect_mcp_schema_rugpull instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'manifest_json' ('audit_profile' defaults to 'strict'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid.

  Parameters:

  • manifest_json (required) — string — JSON string or object containing the external MCP server's tools array to audit.
  • audit_profile — string — Sensitivity level for flagging system-tool name shadowing; defaults to 'strict' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• detect_mcp_schema_rugpull read-only

  Computes structural diffs between a pinned baseline MCP tools/list snapshot and a live server response to catch mid-session description or schema tampering. Use when verifying that a connected MCP server has not mutated its tool definitions mid-session; for performing a first-time static security audit on a single MCP manifest, use audit_mcp_server_manifest instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'baseline_tools_json' ('current_tools_json' defaults to 'standard'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.

  Parameters:

  • baseline_tools_json (required) — string — JSON-serialized baseline tools/list array captured when the MCP server was first trusted.
  • diff_mode — string — Comparison strictness across descriptions and inputSchema; defaults to 'full_structural' when omitted.
  • current_tools_json — string — JSON-serialized live tools/list array to compare against the baseline; defaults to '[]' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• validate_mcp_sampling_request read-only

  Audits inbound MCP sampling/createMessage callbacks from connected servers to block cross-server context snooping (includeContext='allServers') and token quota hijacking. Use when filtering a connected MCP server's request to sample the host LLM; for scrubbing text returned from a standard synchronous tools/call response, use sanitize_tool_output_stream instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'sampling_request_json' ('max_tokens_ceiling' defaults to '512'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.

  Parameters:

  • sampling_request_json (required) — string — JSON string or object representing the inbound MCP sampling/createMessage payload.
  • max_tokens_ceiling — string — Maximum completion token quota allowed for server callbacks; defaults to '2048' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• sanitize_tool_output_stream read-only

  Sanitizes untrusted external tool or web-scrape outputs by stripping invisible Unicode Tag characters (U+E0000), neutralizing Markdown tracking image beacons, and defusing indirect prompt overrides. Use when cleaning raw third-party tool outputs or scraped web text before inserting it into the LLM context window; for redacting personal identifiable information (emails, SSNs, keys) from outbound text, use redact_sensitive_pii instead. Read-only edge call (32 KB, 60 RPM): accepts 'raw_tool_output' (with enum defaults), uses '?demo=true' or L402 (15 sats); HTTP 400 if invalid.

  Parameters:

  • raw_tool_output (required) — string — Untrusted text returned by an external tool, webhook, or web scraper.
  • wrap_tag — string — XML isolation wrapper applied around the sanitized text; defaults to 'tool_data' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• redact_sensitive_pii read-only

  Redacts emails, phone numbers, SSNs, credit cards, API keys, and crypto private keys from text before logging or external transmission. Use when stripping personal data or secret credentials from prompts, logs, or outbound messages; for neutralizing indirect prompt injections and invisible Unicode in inbound tool responses, use sanitize_tool_output_stream instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('redaction_style' defaults to 'typed_token'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid.

  Parameters:

  • text (required) — string — Input text containing potential PII or secret keys to redact.
  • redaction_style — string — Placeholder format used for redacted spans; defaults to 'typed_token' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• detect_agent_action_loop read-only

  Analyzes an agent's recent tool-call trace to detect identical retry spins, A/B state oscillation, and runaway token burn. Use when monitoring autonomous agent execution loops to decide whether to continue or trip a token-burn breaker; for inspecting a single command payload for security threats before execution, use verify_agent_command_safety instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'action_trace_json' ('sensitivity' defaults to 'strict_2_repeats'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • action_trace_json (required) — string — JSON-serialized array of recent agent actions (e.g. '[{"tool":"search","status":"err"}]').
  • sensitivity — string — Cycle detection threshold; defaults to 'standard_3_repeats' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• verify_a2a_agent_card read-only

  Verifies a remote agent's A2A /.well-known/agent.json discovery card, checking JWS/DID signature binding, endpoint HTTPS enforcement, and capability spoofing. Use when authenticating a peer autonomous agent before delegating subtasks or exchanging payments over A2A; for auditing an MCP tool server's tools/list manifest rather than a peer agent's A2A card, use audit_mcp_server_manifest instead. Read-only edge call (32 KB, 60 RPM): accepts 'agent_card_json' ('trust_policy' defaults to 'require_https_and_did'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • agent_card_json (required) — string — JSON string or object of the peer agent's /.well-known/agent.json descriptor.
  • trust_policy — string — Verification policy for DID/DNS binding; defaults to 'require_https_and_did' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• audit_outbound_egress_url read-only

  Static validation firewall for outbound network destination URIs against cloud metadata IP addresses (169.254.169.254), RFC 1918 private IP blocks, and query-string secret exfiltration before agent dispatch. Use when validating a user-supplied or tool-supplied URI destination before network dispatch; for auditing local shell commands or general prompts, use verify_agent_command_safety instead. Read-only edge call (32 KB, 60 RPM): accepts 'destination_uri' ('egress_policy' defaults to 'block_private_and_metadata'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • destination_uri (required) — string — Outbound HTTP/HTTPS destination URI to inspect before fetching (e.g. 'https://api.example.com/v1/webhook').
  • egress_policy — string — Network egress policy; defaults to 'block_private_and_metadata' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• audit_response_factuality read-only

  Cross-references factual claims, numbers, and citations in a draft agent response against retrieved source passages to flag unsupported hallucinations before delivery. Use when verifying that a generated answer is 100% grounded in source evidence before returning it to the user; for scrubbing inbound tool outputs for prompt-injection and invisible Unicode, use sanitize_tool_output_stream instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'claim' ('context' defaults to 'standard'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid.

  Parameters:

  • claim (required) — string — Draft agent response or factual statement to verify for hallucinations.
  • context (required) — string — Authoritative source text or retrieved RAG passages that the claim must be grounded in.
  • strictness — string — Entailment threshold required for numbers and dates; defaults to 'exact_entailment' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• audit_smart_contract_code read-only

  Statically audits Solidity, Vyper, or Move smart contract source code for honeypot transfer taxes, hidden mint backdoors, proxy upgrade traps, and reentrancy. Use when auditing smart contract source code or bytecode before deploying or interacting with a protocol; for scanning Solana Anchor/Rust programs specifically for Cross-Program Invocation (CPI) signer/account vulnerabilities, use scan_solana_cpi_reentrancy instead. Read-only edge call (32 KB, 60 RPM): accepts 'code_or_address' ('chain' defaults to 'evm_solidity'), uses '?demo=true' or L402 (45 sats); HTTP 400 if invalid.

  Parameters:

  • code_or_address (required) — string — Smart contract source code snippet, ABI, or contract address to audit.
  • chain — string — Target blockchain VM architecture; defaults to 'evm_solidity' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• diff_agent_memory_checkpoint read-only

  Computes structural diffs between two agent state snapshots ('added_keys', 'mutated_keys', 'removed_keys'), flags boolean belief contradictions, generates an RFC 7396 JSON Merge Patch delta, and computes a canonical checkpoint hash. Use when checkpointing agent state or transmitting minimal RFC 7396 state deltas across multi-agent handoffs; for counting BPE tokens and auditing Lost-in-the-Middle prompt attention, use plan_context_token_budget instead. Read-only call (32 KB, 60 RPM): accepts 'previous_state_json' (with enum defaults), uses '?demo=true' or L402 (10 sats); HTTP 400 if invalid.

  Parameters:

  • previous_state_json (required) — string — JSON string or object representing the prior agent state snapshot.
  • current_state_json (required) — string — JSON string or object representing the updated agent state snapshot.
  • conflict_strategy — string — Resolution policy when keys conflict; defaults to 'prefer_current' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• heal_malformed_json read-only

  Deterministic JSON syntax repair: normalizes quotes, unclosed brackets, and boolean literals into compliant RFC 8259 JSON structure without data deletion. Use when fixing syntax-broken JSON strings that fail JSON.parse(); for coercing field types and verifying properties on already-parseable JSON objects against a target JSON Schema, use enforce_json_schema_types instead. Read-only edge call (32 KB, 60 RPM): accepts 'malformed_json' (with enum defaults), uses '?demo=true' or L402 (15 sats); HTTP 400 if invalid.

  Parameters:

  • malformed_json (required) — string — Raw broken, truncated, or markdown-wrapped JSON string to repair.
  • repair_mode — string — Bracket-closing and literal-normalization strategy; defaults to 'heuristic_fast' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• enforce_json_schema_types read-only

  Validates a raw LLM output object against a target JSON Schema, automatically coercing mismatched scalar types (e.g. string '42' to integer 42), injecting schema defaults, and pruning undeclared hallucinated fields. Use when enforcing schema compliance and type safety on structured LLM outputs before passing them to typed APIs; for healing unparseable raw JSON text with broken quotes or trailing commas, use heal_malformed_json instead. Read-only edge call (32 KB, 60 RPM): accepts 'raw_output' (with enum defaults), uses '?demo=true' or L402 (15 sats); HTTP 400 if invalid.

  Parameters:

  • raw_output (required) — string — JSON string or object produced by an LLM to validate and coerce.
  • coercion_policy — string — Policy for handling extra undeclared properties; defaults to 'prune_undeclared_and_coerce' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• clean_tabular_dataset read-only

  Deduplicates repetitive lines or records, normalizes Unicode whitespace, strips HTML/control noise, and canonicalizes tabular text or JSON arrays. Use when cleaning noisy scraped lists, CSV rows, or duplicate log lines before indexing or analysis; for extracting typed JSON fields from free-form prose paragraphs, use extract_structured_json_entities instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'data' ('normalization_mode' defaults to 'exact_match'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • data (required) — string — Raw newline-delimited text, CSV rows, or JSON array string to deduplicate and normalize.
  • normalization_mode — string — Deduplication key sensitivity; defaults to 'case_insensitive_trim' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• synthesize_safe_regex read-only

  Synthesizes linear-time O(n) regular expressions free of catastrophic backtracking (ReDoS) and validates them against positive and negative test strings. Use when generating and verifying a regular expression pattern for input validation or lexical parsing; for repairing broken JSON syntax directly without writing custom regexes, use heal_malformed_json instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'description' ('flavor' defaults to 'ecmascript_js'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • description (required) — string — Natural-language specification of the text pattern to match (e.g. 'RFC 5322 email addresses excluding plus-aliases').
  • flavor — string — Target regular expression engine syntax; defaults to 'ecmascript_js' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• compile_xml_agent_prompt read-only

  Compiles a raw task description into a structured XML system prompt (<role>, <context>, <objective>, <constraints>, <workflow>, <output_format>) engineered to prevent instruction drift. Use when authoring or upgrading a system prompt for an autonomous agent or sub-agent workflow; for mapping a task objective to a concrete sequence of MCP tool calls, use route_mcp_workflow_plan instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'task' ('prompt_style' defaults to 'anthropic_xml_tags'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.

  Parameters:

  • task (required) — string — Raw task instructions, persona goal, and operational constraints to compile.
  • prompt_style — string — Structural formatting template; defaults to 'anthropic_xml_tags' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• verify_context_compaction_fidelity read-only

  Audits a compacted conversation summary against the original full context to detect dropped user constraints, lost file paths, altered numbers, or missing pending tasks. Use when verifying that an LLM context-compaction summary retained all task-critical facts before truncating history; for generating a new executive summary from a raw technical document, use summarize_technical_document instead. Read-only edge call (32 KB, 60 RPM): accepts 'original_context' ('compacted_summary' defaults to 'standard'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • original_context (required) — string — Full pre-compaction conversation history or task log.
  • compacted_summary (required) — string — Candidate compacted summary to audit for dropped constraints or entities.
  • audit_focus — string — Entity class prioritized during retention scoring; defaults to 'constraints_paths_and_numbers' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• route_mcp_workflow_plan read-only

  Maps a natural-language agent goal to an ordered sequence of Diogenes MCP tool calls with exact endpoint paths, JSON-RPC 2.0 payloads, and cumulative satoshi cost estimates. Use when an autonomous agent needs to plan which MCP tools to chain together to solve a multi-step objective within a satoshi budget; for compiling a static XML system prompt rather than an executable MCP tool call sequence, use compile_xml_agent_prompt instead. Read-only edge call (32 KB, 60 RPM): accepts 'objective' ('budget_preference' defaults to 'lowest_sats_deterministic'), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid.

  Parameters:

  • objective (required) — string — Natural-language description of the workflow goal to route across MCP tools.
  • budget_preference — string — Cost vs depth routing trade-off; defaults to 'lowest_sats_deterministic' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• arbitrate_agent_deliverable_escrow read-only

  Evaluates a worker agent's submitted task deliverable against agreed contract acceptance criteria to issue a deterministic escrow settlement verdict ('RELEASE_FUNDS_TO_WORKER_AGENT', 'REQUEST_REVISION', or 'REFUND_CLIENT'). Use when settling multi-agent bounties or verifying subcontractor deliverables before releasing MPP/L402 escrow funds; for checking syntactic JSON Schema property types without evaluating semantic contract terms, use enforce_json_schema_types instead. Read-only call (32 KB, 60 RPM): accepts 'deliverable' (with enum defaults), uses '?demo=true' or MPP (30 sats); HTTP 400 if invalid.

  Parameters:

  • deliverable (required) — string — JSON string or text deliverable submitted by the worker agent.
  • terms — string — Contract acceptance criteria that the deliverable must satisfy; defaults to 'Complete verified JSON deliverable' when omitted.
  • arbitration_standard — string — Strictness of contract verification; defaults to 'strict_all_criteria' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• prune_context_skeleton read-only

  Compresses large source files, logs, or transcripts by 50–80% to fit an LLM context budget while preserving 100% of function/class/type signatures, imports, error frames, and query-matched lines. Use when shrinking oversized source files or logs before feeding them into an LLM prompt; for counting BPE tokens across prompt segments and calculating multi-model inference costs without altering text, use plan_context_token_budget instead. Read-only edge call (32 KB, 60 RPM): accepts 'content' (with enum defaults), uses '?demo=true' or L402 (10 sats); HTTP 400 if invalid.

  Parameters:

  • content (required) — string — Raw source code, document, or multi-turn transcript to compress.
  • focus_query — string — Optional symbol or keyword query whose matching lines receive maximum retention priority.
  • pruning_mode — string — Salience weighting preset; defaults to 'ast_signatures_first' when omitted.
  • target_ratio — number — Target token retention ratio between 0.15 and 0.85; defaults to 0.45 when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• plan_context_token_budget read-only

  Counts subword BPE tokens across prompt segments, detects high-priority instructions trapped in the 35%–72% Lost-in-the-Middle attention trough, and calculates USD/satoshi costs across frontier LLMs. Use when auditing prompt token budgets, reordering prompt sections for primacy/recency attention, or comparing model API costs; for actively compressing and stripping low-salience lines from a single large file, use prune_context_skeleton instead. Read-only edge call (32 KB, 60 RPM): accepts 'segments_json' (with enum defaults), uses '?demo=true' or L402 (10 sats); HTTP 400 if invalid.

  Parameters:

  • segments_json (required) — string — JSON string or array of prompt segments '[{"name":"sys","text":"...","priority":10}]' to analyze.
  • max_context_tokens — number — Target model context window limit in tokens; defaults to 128000 when omitted.
  • target_model_family — string — Primary model family for token-Window calibration; defaults to 'gemini_3_1' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• rerank_hybrid_rag_chunks read-only

  Reranks and deduplicates candidate RAG or retrieval passages against a search prompt using Okapi BM25 (k1=1.5, b=0.75), Reciprocal Rank Fusion (RRF), and Maximal Marginal Relevance (MMR) Jaccard diversity filtering. Use when selecting the top-K highest-signal, non-redundant passages from vector search or grep results; for compressing a single contiguous source file while keeping its original line order, use prune_context_skeleton instead. Read-only edge call (32 KB, 60 RPM): accepts 'search_prompt' ('documents_json' defaults to 'standard'), uses '?demo=true' or L402 (15 sats); HTTP 400 if invalid.

  Parameters:

  • search_prompt (required) — string — Technical search prompt or question used to score candidate chunks.
  • documents_json (required) — string — JSON string or array of candidate chunks '[{"id":"c1","text":"..."}]' to rerank.
  • top_k — number — Maximum number of deduplicated chunks to return; defaults to 5 when omitted.
  • ranking_mode — string — Fusion weighting between lexical BM25 and diversity penalty; defaults to 'bm25_rrf_mmr' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• apply_fuzzy_code_patch read-only

  Applies unified diffs (@@ ... @@) or SEARCH/REPLACE blocks to source code using sliding-window token similarity to resolve drifted line numbers, align indentation, and verify bracket balance. Use when healing and applying a code edit or diff that failed exact line matching due to line-number drift or whitespace differences; for inspecting function signatures, call trees, and cyclomatic complexity without modifying code, use analyze_ast_symbol_graph instead. Read-only call (32 KB, 60 RPM): accepts 'original_code' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid.

  Parameters:

  • original_code (required) — string — Complete original source file content before patching.
  • patch (required) — string — Unified diff hunk or <<<<<<< SEARCH ... ======= ... >>>>>>> REPLACE block to apply.
  • fuzz_strategy — string — Line-matching tolerance and indentation behavior; defaults to 'whitespace_normalized_auto_indent' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• analyze_ast_symbol_graph read-only

  Static lexer and AST parser only (zero execution or evaluation): extracts imports, exports, classes, interfaces, and functions with line numbers, intra-file call edges, McCabe cyclomatic complexity, and Halstead volume across TypeScript, Python, Rust, Go, and Move. Use when mapping internal functions, call graphs, and complexity hotspots of a source file before refactoring; for analyzing cross-file import DAGs and circular dependencies, use audit_module_dependency_cycles instead. Read-only call (32 KB, 60 RPM): accepts 'source_text' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid.

  Parameters:

  • code (required) — string — Source code file content to parse for symbols and complexity metrics.
  • language — string — Programming language grammar used for symbol extraction; defaults to 'typescript' when omitted.
  • source_text — string — Alias for code: source code file content to parse.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• audit_module_dependency_cycles read-only

  Runs Tarjan's Strongly Connected Components (SCC) algorithm on a module import map to detect circular dependencies, compute parallel topological build waves, and trace downstream change blast radius. Use when auditing multi-file import graphs for circular cycles or determining which downstream files must be re-tested after an edit; for extracting function-level symbols and cyclomatic complexity inside a single source file, use analyze_ast_symbol_graph instead. Read-only call (32 KB, 60 RPM): accepts 'modules_json' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid.

  Parameters:

  • modules_json (required) — string — JSON string or object mapping each module name to its array of imported module names (e.g. '{"a":["b"],"b":[]}').
  • analysis_scope — string — Graph analysis output mode; defaults to 'cycles_waves_and_blast_radius' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• isolate_stacktrace_root_cause read-only

  Parses noisy CI/terminal logs and multi-language stack traces (Node/TS, Python, Rust, Go), strips node_modules/stdlib frames to isolate the innermost failing user-code frame, and clusters repetitive logs into Drain templates. Use when triage-debugging test failures, crash dumps, or repetitive server error logs; for compressing general source code files or prose transcripts, use prune_context_skeleton instead. Read-only edge call (32 KB, 60 RPM): accepts 'raw_log' ('runtime_hint' defaults to 'auto_detect'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • raw_log (required) — string — Raw terminal output, CI failure log, or exception traceback to analyze.
  • runtime_hint — string — Runtime stack format hint; defaults to 'auto_detect' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• compile_polyglot_type_schemas read-only

  Inspects a sample JSON payload (inferring UUID, ISO-8601 datetime, email, integer vs float, and array item types) and compiles strict TypeScript interfaces, Zod schemas, Python Pydantic v2 models, and JSON Schema Draft 2020-12. Use when generating static type definitions and runtime validators in TypeScript and Python from a sample JSON response; for extracting existing function/class symbols and complexity metrics from source code, use analyze_ast_symbol_graph instead. Read-only call (32 KB, 60 RPM): accepts 'sample_json' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid.

  Parameters:

  • sample_json (required) — string — JSON string or object representing the sample payload to infer types from.
  • root_name — string — Identifier used for the generated root interface/class; defaults to 'GeneratedPayload' when omitted.
  • strictness — string — Schema additionalProperties and format constraint mode; defaults to 'strict_formats' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• evaluate_deterministic_math read-only

  Strict Shunting-Yard AST arithmetic parser with zero eval() or dynamic code execution: evaluates algebraic formulas and computes exact financial NPV, Newton-Raphson IRR, Kelly criterion, and dataset stats. Use when computing exact arithmetic formulas, cashflow NPV/IRR, or descriptive statistics without LLM floating-point guesswork; for running two-sample A/B hypothesis tests, use evaluate_ab_statistical_significance instead. Read-only edge call (32 KB, 60 RPM): accepts 'math_formula' ('precision_digits' defaults to '2_decimals'), uses '?demo=true' or L402 (10 sats); HTTP 400 if invalid.

  Parameters:

  • expression (required) — string — Algebraic or scientific formula to evaluate (e.g. '(125000 * (1 + 0.0725/12)^60) - 98450.50').
  • math_formula — string — Alias for expression: algebraic formula to evaluate.
  • precision_digits — string — Decimal rounding precision for returned numbers; defaults to '8_decimals' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• schedule_critical_path_tasks read-only

  Solves a task dependency DAG via the Critical Path Method (CPM) to compute ES/EF/LS/LF, Total Float/Slack, optimal makespan, and the Critical Path. Use when scheduling dependent engineering milestones or workflow steps to find the minimum project duration and zero-slack bottleneck path; for detecting circular code imports and file blast radius without task durations, use audit_module_dependency_cycles instead. Read-only edge call (32 KB, 60 RPM): accepts 'tasks_json' ('time_unit' defaults to 'minutes'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.

  Parameters:

  • tasks_json (required) — string — JSON string or array of tasks '[{"id":"t1","duration":3,"dependencies":[]}]' to schedule.
  • time_unit — string — Duration unit label attached to the schedule; defaults to 'hours' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• evaluate_ab_statistical_significance read-only

  Computes Welch's two-sample t-test or two-proportion z-test, returning two-tailed p-values, Cohen's d effect size, relative lift %, and Bayesian P(Treatment > Control). Use when determining whether a prompt change, model benchmark, or A/B experiment produced a statistically significant improvement; for evaluating single algebraic formulas or NPV/IRR cashflows, use evaluate_deterministic_math instead. Read-only edge call (32 KB, 60 RPM): accepts 'control_json' ('treatment_json' defaults to 'standard'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • control_json (required) — string — JSON string or object for the baseline control arm (e.g. '{"conversions":142,"total":1000}' or '{"samples":[12,15,14]}').
  • treatment_json (required) — string — JSON string or object for the candidate treatment arm (e.g. '{"conversions":186,"total":1000}').
  • significance_level — string — Type-I error alpha threshold for statistical significance; defaults to 'alpha_0_05' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• detect_openapi_breaking_changes read-only

  Compares baseline and candidate OpenAPI 3.1 specs, JSON Schemas, or MCP tool manifests to detect breaking changes (removed fields, new required inputs, narrowed enums, type mutations). Use when auditing API, JSON Schema, or MCP contract revisions for backward compatibility before deployment; for compiling new TypeScript, Zod, and Pydantic schemas from a single sample JSON payload, use compile_polyglot_type_schemas instead. Read-only edge call (32 KB, 60 RPM): accepts 'baseline_schema_json' (with enum defaults), uses '?demo=true' or L402 (25 sats); HTTP 400 if invalid.

  Parameters:

  • baseline_schema_json (required) — string — JSON string of the baseline OpenAPI 3.1 spec, JSON Schema, or MCP tools array.
  • candidate_schema_json (required) — string — JSON string of the proposed candidate schema or contract revision to compare.
  • contract_format — string — Contract specification format; defaults to 'auto_detect' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• generate_boundary_test_vectors read-only

  Synthesizes deterministic unit-test vectors from a JSON Schema or function signature covering valid equivalence partitions, numeric/length boundaries, and adversarial Unicode/null inputs. Use when generating exhaustive edge-case unit test payloads and fuzz vectors for an API endpoint or function; for healing and applying unified diffs or search/replace edits to source code, use apply_fuzzy_code_patch instead. Read-only edge call (32 KB, 60 RPM): accepts 'schema_or_signature_json' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid.

  Parameters:

  • schema_or_signature_json (required) — string — JSON Schema object or function parameter specification to generate test vectors for.
  • vector_suite_profile — string — Test generation coverage profile; defaults to 'equivalence_boundary_and_fuzz' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• simulate_monte_carlo_risk read-only

  Runs a reproducible seeded Mulberry32 Monte Carlo simulation over uncertain cost, latency, or duration variables to compute P10/P50/P90/P95 percentiles, Value-at-Risk (VaR), and CVaR. Use when modeling stochastic uncertainty, tail risk (VaR/CVaR), and probability of meeting a budget or SLA target; for evaluating deterministic single-point algebraic formulas or exact NPV/IRR cashflows, use evaluate_deterministic_math instead. Read-only edge call (32 KB, 60 RPM): accepts 'variables_json' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid.

  Parameters:

  • variables_json (required) — string — JSON array of stochastic variables (e.g. name, min, mode, max) to simulate.
  • distribution_model — string — Probability distribution family applied to each variable; defaults to 'triangular_pert' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scan_solana_cpi_reentrancy read-only

  Scans Solana Anchor and native Rust program instructions for unverified Cross-Program Invocation (CPI) program IDs, missing signer checks, and PDA bump seed canonicalization bugs. Use when auditing Solana Rust/Anchor source code or instruction account structs for CPI privilege escalation; for checking live SPL token mint/freeze authorities and rug-pull risk by mint address, use evaluate_solana_token_risk instead. Read-only edge call (32 KB, 60 RPM): accepts 'rust_source_or_idl' ('framework' defaults to 'anchor'), uses '?demo=true' or L402 (30 sats); HTTP 400 if invalid.

  Parameters:

  • rust_source_or_idl (required) — string — Solana Rust/Anchor source code or IDL JSON string to scan for CPI vulnerabilities.
  • framework — string — Solana program framework used; defaults to 'anchor' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• evaluate_solana_token_risk read-only

  Evaluates a Solana SPL token's rug-pull probability by checking active mint authority, freeze authority, mutable metadata, and top-holder concentration. Use when making a pre-trade security decision on whether a Solana SPL token is safe to buy; for retrieving SPL token symbol, decimals, and DEX liquidity pool metadata via x402, use inspect_solana_token_liquidity instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'token_address' ('risk_profile' defaults to 'strict_decentralized'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.

  Parameters:

  • token_address (required) — string — Base58-encoded Solana SPL token mint address (32–44 characters).
  • risk_profile — string — Tolerance policy for centralized freeze authorities; defaults to 'strict_decentralized' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• inspect_solana_token_liquidity read-only

  Retrieves canonical Solana SPL token metadata including name, ticker symbol, decimal precision, and current mint/freeze authority addresses. Use when resolving SPL token decimals, ticker symbols, and registry metadata for portfolio or swap formatting; for computing a composite security risk score and binary should_transact verdict, use evaluate_solana_token_risk instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'mint' ('network' defaults to 'mainnet-beta'), supports '?demo=true' or x402 (20 sats), and returns HTTP 400 if invalid.

  Parameters:

  • mint (required) — string — Base58-encoded Solana SPL token mint address (e.g. 'EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v').
  • network — string — Solana cluster to query; defaults to 'mainnet-beta' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• track_solana_whale_flows read-only

  Tracks 24-hour net accumulation or distribution flows across top Solana whale wallets and flags coordinated insider wallet clusters for a given SPL token. Use when analyzing on-chain smart-money order flow and holder clustering on Solana; for checking static SPL contract mint/freeze authority permissions, use evaluate_solana_token_risk instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'token' ('window' defaults to '1h'), supports '?demo=true' or x402 (50 sats), and returns HTTP 400 if invalid.

  Parameters:

  • token (required) — string — Base58 Solana SPL token mint address or ticker symbol to track whale flows for.
  • window — string — Aggregation lookback window for net whale flow; defaults to '24h' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• estimate_solana_priority_fees read-only

  Calculates optimal Solana compute-unit (CU) microlamport priority fees and Jito bundle tip lamports to achieve target block-inclusion probability. Use when setting SetComputeUnitPrice and Jito tips before broadcasting a Solana transaction; for querying Bitcoin L1 sat/vB mempool fee rates, use estimate_bitcoin_mempool_fees instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'priority_level' ('tx_type' defaults to 'simple_transfer'), supports '?demo=true' or x402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • priority_level (required) — string — Target inclusion urgency tier on Solana mainnet-beta.
  • tx_type — string — Transaction category used to estimate compute unit limit; defaults to 'dex_swap' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• decode_eip712_permit_signature read-only

  Decodes EIP-712 and Uniswap Permit2 off-chain typed-data payloads to verify spender identity, detect unlimited (uint256.max) token approvals, and flag expired deadlines. Use when inspecting an off-chain eth_signTypedData_v4 or Permit2 payload before signing; for decoding raw on-chain hex transaction calldata (0x...) for eth_sendTransaction, use simulate_evm_transaction_calldata instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'typed_data_json' ('chain_id' defaults to '1'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.

  Parameters:

  • typed_data_json (required) — string — JSON string or object containing the EIP-712 / Permit2 message (spender, amount, deadline).
  • chain_id — string — EVM chain ID used to verify canonical router spender addresses; defaults to '8453' (Base) when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• simulate_evm_transaction_calldata read-only

  Decodes raw EVM hexadecimal transaction calldata (0x...) by 4-byte function selector to expose hidden ERC-20 approve/transferFrom calls, setApprovalForAll drains, and multicall bundles. Use when auditing raw hex transaction data (to, value, data) before broadcasting an on-chain EVM transaction; for inspecting off-chain EIP-712 JSON typed-data signatures, use decode_eip712_permit_signature instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'calldata_hex' ('network' defaults to 'base_mainnet'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.

  Parameters:

  • calldata_hex (required) — string — Hexadecimal EVM transaction data string starting with '0x' (e.g. '0x095ea7b3000000000000000000000000...').
  • network — string — Target EVM network for simulation context; defaults to 'base_mainnet' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• evaluate_dex_mev_risk read-only

  Evaluates decentralized exchange (DEX) swap parameters against pool depth and mempool visibility to quantify MEV sandwich risk and compute optimal slippage tolerance in basis points. Use when configuring slippage tolerance and private-RPC routing before executing an on-chain DEX token swap; for comparing cross-chain bridge settlement routes across different L1 blockchains, use compare_crosschain_bridge_routes instead. Read-only edge call (32 KB, 60 RPM): accepts 'pair' ('execution_venue' defaults to 'uniswap_v3_public'), uses '?demo=true' or L402 (25 sats); HTTP 400 if invalid.

  Parameters:

  • pair (required) — string — Trading pair symbol or pool identifier (e.g. 'ETH/USDC' or 'SOL/USDC').
  • execution_venue — string — Target DEX protocol or RPC relay; defaults to 'uniswap_v3_public' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• detect_address_poisoning_scam read-only

  Compares a target recipient wallet address against recent transaction history to detect vanity prefix/suffix lookalike spoofing and zero-value dusting attacks. Use when verifying a recipient EVM or Solana wallet address before sending funds; for decoding hex smart contract calldata payloads, use simulate_evm_transaction_calldata instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'target_address' ('address_standard' defaults to 'auto_detect'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.

  Parameters:

  • target_address (required) — string — Candidate recipient EVM (0x...) or Solana Base58 wallet address to verify.
  • address_standard — string — Address encoding format; defaults to 'auto_detect' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• verify_http402_payment_challenge read-only

  Decodes inbound HTTP 402 Payment Required challenges (L402 BOLT11 + Macaroon, x402 Solana USDC, MPP Base intents) to verify cryptographic payment-hash binding and block overcharge fraud. Use when auditing a 402 challenge header before an autonomous agent pays a Lightning invoice or USDC transfer; for checking on-chain Bitcoin L1 mempool feerates, use estimate_bitcoin_mempool_fees instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'www_authenticate' ('protocol_hint' defaults to 'L402'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • www_authenticate (required) — string — Raw WWW-Authenticate or Payment-Required HTTP header string from a 402 response.
  • protocol_hint — string — Expected HTTP 402 payment protocol; defaults to 'L402' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• estimate_bitcoin_mempool_fees read-only

  Fetches real-time Bitcoin mainnet mempool feerate recommendations in satoshis per virtual byte (sat/vB) across fastest, half-hour, hour, and economy confirmation tiers. Use when checking current Bitcoin L1 network congestion before broadcasting an on-chain BTC transaction; for calculating exact SegWit/Taproot UTXO batch consolidation vByte weights and dust thresholds, use plan_bitcoin_utxo_consolidation instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'confirmation_target', supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • confirmation_target — string — Target confirmation speed tier; defaults to 'half_hour' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• plan_bitcoin_utxo_consolidation read-only

  Analyzes a set of Bitcoin UTXO balances in satoshis to compute exact vByte transaction weight, identify uneconomical dust inputs, and recommend whether to consolidate now or hold. Use when optimizing on-chain Bitcoin treasury UTXO sets to minimize long-term miner fee drag; for fetching current live Bitcoin mempool sat/vB feerates alone, use estimate_bitcoin_mempool_fees instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'utxos_sats_json' ('script_type' defaults to 'p2wpkh_segwit'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.

  Parameters:

  • utxos_sats_json (required) — string — JSON array or comma-separated list of UTXO values in satoshis (e.g. '[1200, 45000, 85000]').
  • script_type — string — Bitcoin input script type determining vByte weight per input; defaults to 'p2wpkh_segwit' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• calculate_spot_swap_rate read-only

  Calculates instantaneous spot exchange rates and equivalent USD, BTC, and satoshi values across BTC, ETH, SOL, SUI, and USDC. Use when converting a token amount into USD or satoshis for invoice pricing or accounting; for quoting executable non-KYC cross-chain bridge routes with bridge fees and settlement times, use compare_crosschain_bridge_routes instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'currency' ('amount' defaults to 'standard'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.

  Parameters:

  • currency (required) — string — Source asset ticker symbol to convert from.
  • amount — number — Quantity of the source asset to convert; defaults to 100 when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• compare_crosschain_bridge_routes read-only

  Compares non-custodial, non-KYC cross-chain swap routes (THORChain native L1 swaps, Maya Protocol, Blockstream Liquid) by basis-point fee, net output sats, and settlement time. Use when routing cross-chain treasury settlements (e.g. Solana USDC or Base ETH into native Bitcoin); for calculating mid-market spot exchange rates without bridge routing fees, use calculate_spot_swap_rate instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'from_asset' ('to_asset' defaults to 'BTC_NATIVE'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.

  Parameters:

  • from_asset (required) — string — Origin chain asset identifier to bridge from.
  • amount — number — Input asset amount to quote; defaults to 100.0 when omitted.
  • to_asset — string — Destination chain asset identifier; defaults to 'BTC_NATIVE' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• generate_gemini_completion read-only

  Generates text completions and structured reasoning across all 45 Google Gemini foundation models (Gemini 4 Argon, 3.1 Pro, 3.8 Flash) with zero Google account or API key required. Use when running single-turn reasoning, coding, or analytical prompts on a specific Gemini model; for delegating multi-step complex tasks that require remote tool execution, use execute_antigravity_agent instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('model' defaults to 'gemini-4-argon'), supports '?demo=true' or L402 (50 sats), and returns HTTP 400 if invalid.

  Parameters:

  • prompt (required) — string — Primary user instruction or reasoning prompt to send to the selected Gemini model.
  • model — string — Target Gemini foundation model identifier; defaults to 'gemini-4-argon' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• execute_antigravity_agent read-only

  Dispatches a complex engineering or operational task to Google's Antigravity autonomous agent for multi-step planning, tool orchestration, and verified execution. Use when solving multi-stage software engineering or workflow tasks that require autonomous planning; for compiling exhaustive multi-source literature and market research dossiers, use conduct_deep_research_investigation instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'input' ('execution_mode' defaults to 'autonomous_verified'), supports '?demo=true' or L402 (150 sats), and returns HTTP 400 if invalid.

  Parameters:

  • input (required) — string — High-level task objective and constraints for the Antigravity autonomous agent.
  • execution_mode — string — Autonomy policy for subtask execution; defaults to 'autonomous_verified' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• conduct_deep_research_investigation read-only

  Runs an iterative, multi-hop investigative research session via Gemini Deep Research Pro, cross-examining primary sources to produce a cited technical report. Use when investigating complex scientific, architectural, or market questions requiring deep multi-hop synthesis; for running a fast single-turn Google Search grounded fact lookup, use search_gemini_grounded_web instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'input' ('depth_tier' defaults to 'quick_synthesis'), supports '?demo=true' or L402 (300 sats), and returns HTTP 400 if invalid.

  Parameters:

  • input (required) — string — Investigative research question, scope, and specific aspects to analyze.
  • depth_tier — string — Research breadth and citation density; defaults to 'exhaustive_report' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• operate_computer_use_agent read-only

  Plans and executes OS-level desktop, browser DOM, and GUI coordinate actions (click, type, scroll, wait) using the Gemini Computer Use agent. Use when automating interactive web UIs or desktop workflows that lack a direct REST API; for running code-first API and terminal automation tasks, use execute_antigravity_agent instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'input' ('viewport_preset' defaults to 'desktop_1080p'), supports '?demo=true' or L402 (200 sats), and returns HTTP 400 if invalid.

  Parameters:

  • input (required) — string — UI automation goal and target webpage or application context.
  • viewport_preset — string — Target screen resolution for coordinate grounding; defaults to 'desktop_1080p' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• search_gemini_grounded_web read-only

  Answers factual queries with live Google Search grounding, returning verified up-to-date answers accompanied by source URLs and grounding metadata. Use when verifying live web facts, documentation updates, or current events in a single low-latency call; for querying geographic places, coordinates, directions, and local business data via Google Maps grounding, use search_gemini_grounded_maps instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('recency_bias' defaults to 'past_24h'), supports '?demo=true' or L402 (75 sats), and returns HTTP 400 if invalid.

  Parameters:

  • prompt (required) — string — Factual question or search query to ground against live Google Search results.
  • recency_bias — string — Temporal preference for search snippets; defaults to 'any_time' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• search_gemini_grounded_maps read-only

  Executes geospatial and point-of-interest queries grounded in live Google Maps data, returning verified addresses, coordinates, operating hours, and spatial context. Use when resolving physical locations, venues, transit distances, or regional infrastructure data; for searching general web articles, documentation, and news, use search_gemini_grounded_web instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('distance_units' defaults to 'metric_km'), supports '?demo=true' or L402 (75 sats), and returns HTTP 400 if invalid.

  Parameters:

  • prompt (required) — string — Geospatial query, place name, or regional routing question.
  • distance_units — string — Preferred unit system for distances; defaults to 'metric_km' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• compile_mpp_research_dossier read-only

  Compiles a structured JSON research dossier ('key_findings', 'synthesis_quality_score', 'sources_cited') settled via Base EVM Machine Payments Protocol (MPP). Use when generating a strict-JSON cited intelligence brief paid via Base USDC MPP session headers; for running long-form narrative research reports via L402 Lightning, use conduct_deep_research_investigation instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'research_topic' ('output_density' defaults to 'concise_5_points'), supports '?demo=true' or MPP (300 sats), and returns HTTP 400 if invalid.

  Parameters:

  • query (required) — string — Research topic or technical question to investigate and structure into JSON.
  • output_density — string — Granularity of the key_findings array; defaults to 'executive_10_points' when omitted.
  • research_topic — string — Alias for query: research topic or technical question to investigate.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• generate_gemini_embeddings read-only

  Generates normalized 3,072-dimensional or 768-dimensional semantic vector embeddings via Google Gemini Embedding 2 for RAG indexing and cosine-similarity search. Use when embedding text passages or queries via L402 Lightning with configurable Matryoshka dimensions; for running live Google Search grounded factual queries, use search_gemini_grounded_web instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('model' defaults to 'gemini-embedding-2'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • text (required) — string — Input text passage, code snippet, or search query to embed into a float vector.
  • model — string — Gemini embedding model version; defaults to 'gemini-embedding-2' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• analyze_omni_multimodal_input read-only

  Analyzes combined multimodal prompts spanning text, image descriptors, audio transcripts, and video temporal events using Gemini Omni Flash. Use when correlating information across multiple media modalities in a single reasoning pass; for running pure text-only reasoning or coding prompts, use generate_gemini_completion instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'input' ('modality_focus' defaults to 'cross_modal_synthesis'), supports '?demo=true' or L402 (100 sats), and returns HTTP 400 if invalid.

  Parameters:

  • input (required) — string — Multimodal prompt or media scene description to analyze.
  • modality_focus — string — Primary analytical lens applied to the multimodal input; defaults to 'cross_modal_synthesis' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• plan_robotics_spatial_trajectory read-only

  Computes 3D spatial affordances, obstacle-avoidance waypoints, and manipulator grasp sequences using Gemini Robotics ER 2 embodied reasoning. Use when planning physical robot arm kinematics, mobile navigation waypoints, or spatial scene task orders; for interacting with 2D desktop or browser GUI screens, use operate_computer_use_agent instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('coordinate_frame' defaults to 'cartesian_xyz_meters'), supports '?demo=true' or L402 (150 sats), and returns HTTP 400 if invalid.

  Parameters:

  • prompt (required) — string — Spatial environment description, obstacle coordinates, and physical manipulation goal.
  • coordinate_frame — string — Reference coordinate convention; defaults to 'cartesian_xyz_meters' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• generate_nano_banana_image read-only

  Generates photorealistic illustrations, UI mockups, and technical diagrams from text prompts using the Nano Banana Pro (Gemini 2.5 Flash Image) model family. Use when creating static visual assets, icons, or architecture diagrams from text descriptions; for synthesizing animated multi-second video clips with motion, use generate_veo_cinematic_video instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('aspect_ratio' defaults to '1:1'), supports '?demo=true' or L402 (75 sats), and returns HTTP 400 if invalid.

  Parameters:

  • prompt (required) — string — Detailed visual scene, composition, lighting, and typography description to render.
  • aspect_ratio — string — Output image aspect ratio; defaults to '16:9' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• generate_veo_cinematic_video read-only

  Synthesizes high-definition cinematic video sequences with temporally coherent camera motion and physics using Google Veo 3. Use when generating moving video clips, product B-roll, or animated scene renders from text prompts; for rendering static single-frame images or diagrams at lower cost, use generate_nano_banana_image instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('motion_style' defaults to 'static_tripod'), supports '?demo=true' or L402 (650 sats), and returns HTTP 400 if invalid.

  Parameters:

  • prompt (required) — string — Cinematic scene description including subject motion, camera trajectory, and lighting.
  • motion_style — string — Camera movement preset; defaults to 'smooth_tracking_shot' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• compose_lyria_music_track read-only

  Composes studio-grade instrumental music tracks, ambient loops, and multi-instrument arrangements from genre, tempo, and mood prompts using Google Lyria 3. Use when generating musical scores, soundtrack stems, or rhythmic audio loops; for converting written text into spoken human voice narration (TTS), use synthesize_gemini_speech_audio instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('genre_preset' defaults to 'cinematic_synth'), supports '?demo=true' or L402 (150 sats), and returns HTTP 400 if invalid.

  Parameters:

  • prompt (required) — string — Musical style, instrumentation, BPM tempo, and harmonic mood description.
  • genre_preset — string — Primary acoustic or electronic genre; defaults to 'cinematic_synth' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• synthesize_gemini_speech_audio read-only

  Converts written text into natural, prosody-controlled spoken voice audio using Gemini 3.8 Flash Neural Text-to-Speech. Use when rendering voiceover narration or spoken agent replies from a deterministic text script; for conducting bidirectional conversational audio dialog comprehension, use process_live_audio_dialogue instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('voice_persona' defaults to 'neutral_broadcast'), supports '?demo=true' or L402 (50 sats), and returns HTTP 400 if invalid.

  Parameters:

  • text (required) — string — Exact written script or paragraph to synthesize into spoken voice audio.
  • voice_persona — string — Expressive vocal timbre preset; defaults to 'neutral_broadcast' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• process_live_audio_dialogue read-only

  Processes real-time conversational dialog turns with native acoustic emotion, interruption handling, and paralinguistic cue comprehension via Gemini 3.8 Live. Use when handling interactive voice-agent dialog turns that require tone and turn-taking awareness; for performing one-way text-to-speech readout of a static text string, use synthesize_gemini_speech_audio instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'input' ('response_tone' defaults to 'direct_peer'), supports '?demo=true' or L402 (75 sats), and returns HTTP 400 if invalid.

  Parameters:

  • input (required) — string — Conversational audio transcript or dialog turn payload to process.
  • response_tone — string — Target paralinguistic delivery style; defaults to 'direct_peer' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• extract_structured_json_entities read-only

  Extracts structured JSON records, named entities, dates, and financial figures from unstructured prose, emails, or HTML/Markdown dumps. Use when converting unstructured natural-language text into a structured JSON array of entities; for validating and coercing an existing JSON payload against a formal JSON Schema, use enforce_json_schema_types instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('extraction_target' defaults to 'general_entities_and_metrics'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid.

  Parameters:

  • text (required) — string — Unstructured document, email body, or webpage text to extract structured entities from.
  • extraction_target — string — Primary entity domain to extract; defaults to 'general_entities_and_metrics' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• synthesize_python_automation_code read-only

  Synthesizes PEP 8 compliant, self-contained Python 3 scripts, data parsers, and CLI utilities complete with type hints, docstrings, and inline assertion tests. Use when generating a standalone Python automation script or parser from a functional specification; for summarizing existing documentation or codebases into executive bullet points, use summarize_technical_document instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('dependency_policy' defaults to 'stdlib_only'), supports '?demo=true' or L402 (75 sats), and returns HTTP 400 if invalid.

  Parameters:

  • prompt (required) — string — Functional specification, input/output formats, and edge cases for the Python script.
  • dependency_policy — string — Allowed library dependencies in generated code; defaults to 'stdlib_only' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• summarize_technical_document read-only

  Condenses long technical specifications, RFCs, research papers, or meeting transcripts into high-density executive bullet points preserving exact figures and decisions. Use when producing a human-readable executive summary of a single provided document; for researching a topic across the live web with Google Search citations, use synthesize_web_intelligence_brief instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('summary_format' defaults to 'executive_bullets'), supports '?demo=true' or L402 (50 sats), and returns HTTP 400 if invalid.

  Parameters:

  • text (required) — string — Full document text, RFC, or transcript to summarize.
  • summary_format — string — Output presentation structure; defaults to 'executive_bullets' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• synthesize_web_intelligence_brief read-only

  Synthesizes a real-time market or technical intelligence brief grounded in live Google Search, returning strict JSON ('executive_summary', 'key_developments', 'sentiment', 'sources'). Use when fetching a structured JSON market/news brief with live web citations and sentiment classification; for summarizing caller-supplied text offline without live web search, use summarize_technical_document instead. Read-only edge call (32 KB, 60 RPM): accepts 'topic' ('focus' defaults to 'technical_and_market_catalysts'), supports '?demo=true' or L402 (75 sats), and returns HTTP 400 if invalid.

  Parameters:

  • topic (required) — string — Company, protocol, market sector, or technical topic to brief.
  • focus — string — Analytical angle applied to the brief; defaults to 'technical_and_market_catalysts' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• infer_mpp_streaming_session read-only

  Initializes a Base USDC Machine Payments Protocol (MPP) metered inference session, allocating a streaming token quota and returning a step-by-step execution plan. Use when running session-metered agent planning settled via Base EVM MPP 'Payment-Challenge' headers; for mapping a task goal to L402 MCP tool calls without opening an MPP streaming session, use route_mcp_workflow_plan instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'task' ('token_quota_tier' defaults to 'compact_1024'), supports '?demo=true' or MPP (100 sats), and returns HTTP 400 if invalid.

  Parameters:

  • task (required) — string — Agent workflow task to execute within the metered MPP session.
  • token_quota_tier — string — Allocated streaming token ceiling for the session; defaults to 'standard_4096' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• generate_x402_vector_embeddings read-only

  Generates normalized high-dimensional semantic vector embeddings settled via Solana SPL USDC ('x402' protocol headers) for decentralized RAG pipelines. Use when computing text embeddings paid via Solana USDC x402 signatures rather than Bitcoin Lightning; for extracting discrete JSON entities from unstructured text, use extract_structured_json_entities instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('encoding_format' defaults to 'float_array'), supports '?demo=true' or x402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • text (required) — string — Input text string or document chunk to convert into a normalized embedding vector.
  • encoding_format — string — Vector serialization format; defaults to 'float_array' when omitted.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• extract_clean_markdown read-only

  Converts raw HTML pages into clean, boilerplate-free, LLM-optimized Markdown with preserved hyperlinks and headings. Use when ingesting raw web documents or blog posts into agent context windows; for isolating tabular data into structured datasets, use parse_html_tables instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' ('conversion_mode' defaults to 'clean_semantic_article'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • html_content (required) — string — Raw HTML string of the web page or document to convert to clean Markdown.
  • preserve_links — boolean — Whether to retain anchor hyperlinks and image markdown references in output.
  • conversion_mode — string — Markdown extraction strategy: clean semantic article, preserve tables/code, or minimal text.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• scrape_readable_article read-only

  Extracts primary article body, author bylines, publication timestamps, and estimated reading duration from web pages. Use when stripping navigation bars, advertisement containers, and cookie banners to isolate core editorial content; for converting full HTML to markdown, use extract_clean_markdown instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' ('readability_profile' defaults to 'article_body_strict'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • html_content (required) — string — Target web page HTML containing the article, editorial post, or blog content.
  • include_byline — boolean — Whether to parse author names, affiliations, and editorial publication dates.
  • readability_profile — string — Content isolation heuristic: strict article body, technical documentation, or forum thread.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• extract_structured_metadata read-only

  Extracts OpenGraph tags, Twitter Card metadata, canonical URLs, and Schema.org JSON-LD microdata scripts from HTML. Use when indexing social share cards, author identity, breadcrumbs, and rich snippet schemas for AI search agents; for scanning page hyperlinks and outbound references, use extract_page_hyperlinks instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' ('metadata_targets' defaults to 'all_protocols'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • html_content (required) — string — Source HTML string containing head tags, OpenGraph meta properties, or JSON-LD scripts.
  • include_favicons — boolean — Whether to extract favicon links and Apple Touch icon references.
  • metadata_targets — string — Target metadata protocol filter: all protocols, OpenGraph and Twitter, or Schema.org JSON-LD.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• parse_html_tables read-only

  Detects and parses HTML table elements into structured JSON record arrays and GitHub-Flavored Markdown tabular grids. Use when converting financial statements, product comparison grids, or sports statistics into structured data tables; for extracting raw clean markdown prose, use extract_clean_markdown instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' ('output_format' defaults to 'markdown_and_json'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • html_content (required) — string — Raw HTML string containing one or more table, thead, tbody, or tr elements.
  • min_rows — integer — Minimum rows required for a table to be parsed and retained.
  • output_format — string — Tabular export formatting standard: markdown and JSON, JSON records only, or CSV string.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• isolate_css_selectors read-only

  Evaluates CSS selector queries against HTML DOM trees to extract targeted inner text, outer HTML, or element attributes. Use when targeting specific elements like pricing badges, product titles, review cards, or navigation breadcrumbs; for parsing unstructured contact information, use extract_contact_info instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' and 'selector_query' ('extraction_mode' defaults to 'inner_text'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • html_content (required) — string — HTML source markup to query against using CSS selector matching rules.
  • selector_query (required) — string — CSS selector query expression (e.g., '.pricing-card', '#main h2', 'article p').
  • extraction_mode — string — DOM extraction representation: text content, outer HTML snippet, or attribute key-value map.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• detect_paywall_and_bypass read-only

  Audits web page DOM hierarchies to detect soft paywalls, blur overlays, modal gates, and recovers concealed body text. Use when diagnosing paywall obstructions, diagnosing subscriber gating scripts, or auditing content access barriers; for assessing general SEO hygiene, use evaluate_seo_diagnostics instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' ('detection_profile' defaults to 'heuristic_dom_overlay'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • html_content (required) — string — Target web page HTML markup suspected of containing soft paywalls or paywall modals.
  • target_domain — string — Optional publishing domain name to look up publisher gating patterns.
  • detection_profile — string — Paywall detection heuristic: heuristic DOM overlay, hidden text recovery, or strict access barrier audit.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• crawl_sitemap_urls read-only

  Parses XML sitemaps and sitemap index files into structured URL trees with change frequency and last-modified filters. Use when discovering domain architectures, mapping crawl frontiers, or indexing blog/product catalogues; for extracting on-page hyperlinks from raw HTML, use extract_page_hyperlinks instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'sitemap_xml' ('filter_criteria' defaults to 'all_entries'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • sitemap_xml (required) — string — XML string of the sitemap or sitemapindex file to inspect and parse.
  • max_results — integer — Maximum number of URLs to extract and return in the catalog.
  • filter_criteria — string — URL retention filter: all entries, recently modified lastmod only, or HTML pages only.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• extract_page_hyperlinks read-only

  Extracts, normalizes, and filters internal and external hyperlinks, anchor texts, and downloadable asset targets from HTML. Use when building site crawlers, auditing broken links, or extracting reference citations; for isolating primary readable article narrative text, use scrape_readable_article instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' ('link_scope' defaults to 'all_links'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • html_content (required) — string — Source HTML string containing anchor tags, href attributes, and link targets.
  • base_url — string — Base URL of the target page for resolving relative link paths.
  • link_scope — string — Link extraction scope: all links, internal domain only, external links only, or download assets.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• sanitize_html_content read-only

  Sanitizes raw HTML by removing malicious script tags, iframes, inline event handlers, and data URIs into safe markup. Use when preparing untrusted third-party web content for rendering in agent dashboards or email clients; for converting clean HTML into markdown, use extract_clean_markdown instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' ('sanitization_strictness' defaults to 'strip_scripts_and_iframes'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • html_content (required) — string — Untrusted or potentially hazardous HTML string requiring sanitization.
  • preserve_images — boolean — Whether to retain safe img elements with http/https sources.
  • sanitization_strictness — string — Sanitizer filter policy: strip scripts and iframes, allowlist safe formatting, or plaintext strip all.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• extract_contact_info read-only

  Extracts email addresses, telephone numbers, physical addresses, and social network handles from web text and DOM footers. Use when researching sales leads, aggregating business contact directories, or extracting customer service info; for parsing structured tabular data, use parse_html_tables instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'content' ('extraction_focus' defaults to 'all_contacts'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • content (required) — string — Raw text or HTML page content to scan for contact channels and lead info.
  • country_hint — string — Two-letter ISO country code for telephone numbering format hints.
  • extraction_focus — string — Contact filter focus: all contact info, emails and phones only, or social handles only.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• evaluate_seo_diagnostics read-only

  Audits HTML heading structures, title lengths, meta descriptions, image alt tags, and OpenGraph compliance into a health score. Use when auditing landing pages, verifying SEO compliance before publishing, or evaluating crawl friendliness; for extracting article bodies, use scrape_readable_article instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' ('audit_level' defaults to 'comprehensive_audit'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • html_content (required) — string — Web page HTML string to evaluate against search engine optimization standards.
  • audit_level — string — Diagnostic audit scope: comprehensive audit, meta tags only, or heading hierarchy only.
  • target_keyword — string — Primary search keyword to check for in titles, headings, and meta tags.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• compile_rss_feed read-only

  Transforms JSON item collections or article card arrays into standardized RSS 2.0, Atom 1.0, or JSON Feed 1.1 syndication feeds. Use when syndicating blog articles, product announcements, or changelog cards to RSS readers and AI agents; for compiling structured sitemap listings, use crawl_sitemap_urls instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'items_json' and 'channel_title' ('feed_standard' defaults to 'rss_2_0'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • items_json (required) — string — JSON string representing an array of article or feed items with title, link, and pubDate.
  • channel_title (required) — string — Headline title for the syndication feed channel.
  • feed_standard — string — Target syndication feed specification: RSS 2.0, Atom 1.0, or JSON Feed 1.1.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• synthesize_neural_search read-only

  Executes multi-domain semantic search query expansion, relevance re-ranking, and extractive factual snippet bundling. Use when retrieving grounded web knowledge, evaluating search results across diverse domains, and retrieving cited answers; for building deep research briefings, use compile_research_dossier instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'search_query' ('search_mode' defaults to 'hybrid_semantic_keyword'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid.

  Parameters:

  • search_query (required) — string — Primary search query, factual question, or technical topic to search.
  • max_results — integer — Maximum number of ranked result snippets to synthesize.
  • search_mode — string — Information retrieval strategy: hybrid semantic keyword, strict fact retrieval, or deep research.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• compile_research_dossier read-only

  Compiles multi-source factual research briefs with verified citations, confidence intervals, and key analytical takeaways. Use when synthesizing comprehensive intelligence briefings on complex technical, scientific, or market developments; for rapid query search snippets, use synthesize_neural_search instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'research_topic' ('depth_level' defaults to 'executive_brief'), supports '?demo=true' or L402 (35 sats), and returns HTTP 400 if invalid.

  Parameters:

  • research_topic (required) — string — Complex subject, market sector, emerging technology, or policy topic to research.
  • depth_level — string — Research dossier rigor: executive brief, deep investigation, or technical whitepaper.
  • target_citations — integer — Target number of primary citations to identify and verify.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• expand_search_queries read-only

  Generates targeted Boolean queries, semantic synonym variations, and sub-question expansions from an ambiguous prompt. Use when overcoming query vocabulary mismatches and expanding search recall across academic, code, or patent databases; for scoping queries to domain categories, use filter_domain_intelligence instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'base_query' ('expansion_strategy' defaults to 'boolean_operators'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • base_query (required) — string — Initial search prompt or ambiguous question requiring semantic query expansion.
  • target_count — integer — Target count of query variations to synthesize.
  • expansion_strategy — string — Query expansion method: Boolean operators, semantic synonyms, or cross-domain questions.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• filter_domain_intelligence read-only

  Scopes search execution and filters results strictly across verified high-reputation domain registries and regulatory bodies. Use when restricting search discovery to verified academic papers, SEC filings, official documentation, or legal statutes; for checking specific factual claims, use verify_factual_claims instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'query' ('domain_tier' defaults to 'academic_and_research'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • query (required) — string — Topic or query to execute across specialized domain registries.
  • domain_tier — string — Curated domain authority tier: academic and research, regulatory and legal, tech docs, or financial.
  • time_horizon — string — Optional recency filter window (e.g., '1y', '5y', 'all_time').

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• analyze_news_recency read-only

  Tracks breaking news feeds, clusters trending story cycles, and calculates story publication velocity over recent timeframes. Use when analyzing breaking market catalysts, emerging controversies, or ongoing product announcements; for evaluating sentiment polarity across media, use analyze_media_sentiment instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'topic' ('recency_window' defaults to 'past_24_hours'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.

  Parameters:

  • topic (required) — string — Subject, ticker symbol, brand, or public event to scan for breaking news developments.
  • recency_window — string — News timestamp search window: past hour, past 24 hours, past 7 days, or past 30 days.
  • sentiment_cluster — boolean — Whether to calculate sentiment direction across news story clusters.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• verify_factual_claims read-only

  Audits factual statements against authoritative consensus sources and assigns truthfulness scores with counter-evidence. Use when checking disputed claims, detecting AI hallucinations, or validating quotes before citation; for formatting academic citations, use extract_scholarly_citations instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'claim_statement' ('verification_rigor' defaults to 'multi_source_consensus'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.

  Parameters:

  • claim_statement (required) — string — Factual assertion, statistic, or quote requiring independent source verification.
  • context_domain — string — Optional domain context such as economics, medicine, history, or computer science.
  • verification_rigor — string — Fact verification method: multi-source consensus, official records only, or probabilistic check.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• extract_scholarly_citations read-only

  Formats academic paper metadata and DOI identifiers into standard scholarly citation formats (BibTeX, APA, IEEE, MLA). Use when generating bibliographies for research papers, validating journal references, or resolving DOI identifiers; for structuring research timelines, use summarize_temporal_timeline instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'source_content_or_doi' ('citation_style' defaults to 'bibtex_format'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • source_content_or_doi (required) — string — DOI string, arXiv ID, or raw paper title with author list to format into citation.
  • citation_style — string — Bibliographic citation standard: BibTeX format, APA 7th edition, IEEE standard, or MLA 9th edition.
  • include_abstract — boolean — Whether to include publication abstract in structured metadata.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• cluster_topic_subgraphs read-only

  Discovers latent thematic clusters, subtopic branches, and conceptual relationships across document corpora. Use when structuring broad search results into distinct thematic silos or generating table of contents taxonomies; for tracking chronological milestones, use summarize_temporal_timeline instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'documents_or_queries' ('clustering_method' defaults to 'tf_idf_semantic_graph'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • documents_or_queries (required) — string — Newline-separated list or JSON array of text snippets, queries, or article abstracts.
  • max_clusters — integer — Maximum number of thematic cluster groups to partition data into.
  • clustering_method — string — Thematic clustering algorithm: TF-IDF semantic graph, centroid k-means, or hierarchical taxonomy.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• analyze_media_sentiment read-only

  Evaluates brand, market, or topic sentiment across news headlines, discussions, and articles with bull/bear polarity scores. Use when assessing market sentiment, social brand perception, or controversy exposure on specific entities; for compiling competitive market comparisons, use compile_competitive_landscape instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text_or_headlines' ('sentiment_domain' defaults to 'general_news'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • text_or_headlines (required) — string — Collection of headlines, commentary strings, or editorial paragraphs to evaluate.
  • entity_filter — string — Optional specific brand, company, or coin name to isolate sentiment around.
  • sentiment_domain — string — Lexicon domain weighting: general news, financial markets, or developer ecosystem.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• rank_expert_sources read-only

  Identifies and ranks top domain authorities, leading researchers, and primary documentation repositories for technical topics. Use when finding primary source experts to cite or discovering foundational documentation for specialized fields; for ranking general search query snippets, use synthesize_neural_search instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'subject_area' ('authority_metric' defaults to 'pagerank_and_domain_authority'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • subject_area (required) — string — Academic field, open source framework, protocol, or technical discipline to explore.
  • max_experts — integer — Maximum number of top domain authorities to return in the ranking.
  • authority_metric — string — Reputation evaluation standard: PageRank and domain authority, citation h-index, or code repo stars.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• summarize_temporal_timeline read-only

  Synthesizes chronological milestone timelines from search results, news archives, and historical documents. Use when reconstructing historical events, tracking company histories, or mapping regulatory progression; for tracking real-time breaking news in the past 24 hours, use analyze_news_recency instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'event_corpus' ('timeline_resolution' defaults to 'chronological_milestones'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • event_corpus (required) — string — Unstructured text corpus containing dated events, news reports, or historical accounts.
  • ascending_order — boolean — Whether to sort timeline from oldest to newest (true) or reverse chronological (false).
  • timeline_resolution — string — Temporal event grouping: chronological milestones, daily chronicle, or weekly epochs.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• compile_competitive_landscape read-only

  Compiles multi-competitor comparison matrices, pricing tiers, feature coverage, and strategic moat evaluations. Use when analyzing market landscapes, evaluating pricing parity, or conducting diligence on competing product offerings; for compiling narrative research briefs, use compile_research_dossier instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'target_entity_or_market' ('analysis_framework' defaults to 'feature_and_pricing_matrix'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid.

  Parameters:

  • target_entity_or_market (required) — string — Industry sector, product category, or target company to benchmark against competitors.
  • max_competitors — integer — Maximum number of market competitors to profile and contrast.
  • analysis_framework — string — Benchmarking framework: feature and pricing matrix, SWOT competitive moat, or market share quadrant.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• synthesize_sql_query read-only

  Translates natural language questions into dialect-accurate, optimized SQL SELECT queries with schema awareness and safety checks. Use when generating reporting queries or automated data analytics pipelines; for analyzing SQL execution performance and EXPLAIN plans, use analyze_query_plan instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'natural_language_request' and 'schema_ddl' ('sql_dialect' defaults to 'postgresql_dialect'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • natural_language_request (required) — string — Natural language question or reporting requirement to transform into SQL.
  • schema_ddl (required) — string — Database schema DDL statements defining available tables, columns, and relations.
  • sql_dialect — string — Target SQL dialect specification: PostgreSQL dialect, MySQL dialect, or SQLite dialect.
  • read_only_mode — boolean — Whether to enforce strict read-only SELECT query constraints.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• audit_sql_injection_ast read-only

  Statically parses SQL queries via AST lexical analysis to detect second-order injection, tautology conditions, and stacked queries. Use when auditing dynamic query parameters or untrusted user input before database execution; for sanitizing query strings for telemetry logging, use sanitize_sql_telemetry instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'raw_sql' ('audit_sensitivity' defaults to 'strict_zero_dynamic_taint'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • raw_sql (required) — string — Raw SQL query string to parse and audit for injection vulnerabilities.
  • allow_comments — boolean — Whether SQL inline comments are allowed or treated as injection vectors.
  • audit_sensitivity — string — Audit sensitivity mode: strict zero dynamic taint, second order injection check, or standard syntax audit.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• analyze_query_plan read-only

  Analyzes SQL EXPLAIN execution plans to detect sequential table scans, high-cost cartesian joins, and buffer memory bottlenecks. Use when diagnosing slow queries, optimizing database performance, or evaluating query cost; for getting index recommendations, use recommend_database_indexes instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'explain_plan_or_query' ('optimization_target' defaults to 'eliminate_seq_scans'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • explain_plan_or_query (required) — string — Raw text or JSON output of EXPLAIN / EXPLAIN ANALYZE or the candidate SQL query.
  • database_engine — string — Database engine name (e.g., 'postgres', 'mysql', 'sqlite').
  • optimization_target — string — Optimization goal: eliminate sequential scans, reduce memory buffers, or minimize join costs.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• detect_breaking_migrations read-only

  Compares source and target DDL schemas to identify breaking changes, destructive column drops, and lock-inducing mutations. Use when verifying CI/CD migration scripts before production deployment to prevent downtime; for verifying relational normal form, use validate_schema_normalization instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'current_schema' and 'target_schema' ('risk_tolerance' defaults to 'zero_downtime_strict'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • current_schema (required) — string — Current production database DDL schema representing live tables and columns.
  • target_schema (required) — string — Proposed new database DDL schema representing target migration state.
  • risk_tolerance — string — Deployment safety policy: zero downtime strict, allow transient locks, or permissive dev.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• transpile_sql_dialect read-only

  Transpiles SQL queries and DDL schemas across PostgreSQL, MySQL, and SQLite dialects, rewriting functions and syntax quirks. Use when migrating application queries across database backends or testing against in-memory SQLite; for generating new queries from natural language, use synthesize_sql_query instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'sql_code' and 'source_dialect' ('target_dialect' defaults to 'sqlite'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • sql_code (required) — string — SQL query or DDL statement to convert from source dialect into target dialect.
  • source_dialect (required) — string — Original SQL dialect of the input code: postgresql, mysql, or sqlite.
  • target_dialect (required) — string — Destination SQL dialect to transpile into: postgresql, mysql, or sqlite.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• recommend_database_indexes read-only

  Recommends optimal single-column and composite B-Tree/BRIN indexes based on slow query WHERE, JOIN, and ORDER BY clauses. Use when optimizing database response times and eliminating full-table scans; for inspecting full execution plans, use analyze_query_plan instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'slow_queries_or_workload' ('index_type_preference' defaults to 'btree_and_composite'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • slow_queries_or_workload (required) — string — Collection of slow SQL queries or workload log statements to analyze for index gaps.
  • max_new_indexes — integer — Maximum number of index creation statements to recommend.
  • index_type_preference — string — Target indexing strategy: B-tree and composite, BRIN and GIN sparse, or covering indexes with INCLUDE.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• validate_schema_normalization read-only

  Audits database schemas for third normal form (3NF) compliance, transitive dependencies, and missing foreign key constraints. Use when reviewing database architectures, preventing update anomalies, or validating relational integrity; for detecting breaking schema migrations, use detect_breaking_migrations instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'schema_ddl' ('target_normal_form' defaults to 'third_normal_form_3nf'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • schema_ddl (required) — string — Database schema DDL statements defining table columns, primary keys, and relations.
  • strict_keys — boolean — Whether to enforce explicit foreign key constraints on all ID references.
  • target_normal_form — string — Target normalization standard: 3NF, Boyce-Codd BCNF, or denormalized OLAP star.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• sanitize_sql_telemetry read-only

  Masks PII, financial values, and credential literals from raw SQL query logs and slow-query dumps before telemetry storage. Use when scrubbing production database query logs before shipping to APM tools, Datadog, or external log collectors; for auditing SQL injection vulnerabilities, use audit_sql_injection_ast instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'query_logs' ('masking_policy' defaults to 'mask_pii_and_literals'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • query_logs (required) — string — Raw SQL query text or multi-line database query log strings requiring sanitization.
  • hash_salt — string — Optional salt string for deterministic pseudonymization of user IDs.
  • masking_policy — string — Scrubbing rigor policy: mask PII and literals, anonymize all constants, or strict AST parameterization.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• synthesize_seed_fixtures read-only

  Generates deterministic relational test seed fixtures respecting foreign key constraints, unique indexes, and data bounds. Use when provisioning mock database datasets for automated testing, staging environments, or sandbox demos; for compiling ORM models from schemas, use generate_orm_models instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'schema_ddl' ('fixture_volume' defaults to 'minimal_smoke_test_5'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • schema_ddl (required) — string — Target database schema DDL defining tables, column types, and foreign key relations.
  • fixture_volume — string — Mock dataset volume profile: minimal smoke test (5), standard dataset (50), or stress dataset (500).
  • deterministic_seed — integer — Integer seed for reproducible pseudo-random data generation.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• calculate_pool_headroom read-only

  Calculates optimal connection pool sizing, idle timeouts, and client headroom based on server RAM and concurrency profile. Use when sizing PgBouncer, HikariCP, or Prisma connection pools to avoid server out-of-memory crashes; for checking transaction isolation hazards, use audit_transaction_isolation instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'server_ram_mb' and 'max_concurrent_clients' ('workload_profile' defaults to 'high_concurrency_oltp'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

  Parameters:

  • server_ram_mb (required) — number — Total available RAM in megabytes dedicated to the database server instance.
  • max_concurrent_clients (required) — number — Peak anticipated concurrent client connections or serverless worker threads.
  • workload_profile — string — Workload operational characteristics: high-concurrency OLTP, heavy analytical OLAP, or serverless edge burst.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• audit_transaction_isolation read-only

  Audits database transaction workflows for concurrency anomalies, dirty reads, non-repeatable reads, and deadlock risks. Use when reviewing financial transfer procedures, inventory decrement operations, or multi-step checkout workflows; for calculating connection pool headroom, use calculate_pool_headroom instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'transaction_steps' ('target_isolation_level' defaults to 'read_committed'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • transaction_steps (required) — string — Sequential SQL commands or description of business operations within the transaction.
  • strict_deadlock_check — boolean — Whether to perform exhaustive cross-table lock acquisition ordering analysis.
  • target_isolation_level — string — Candidate SQL isolation level: read committed, repeatable read, or serializable.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• generate_orm_models read-only

  Compiles SQL DDL schemas into type-safe ORM entities and TypeScript validation schemas (Prisma, Drizzle, SQLAlchemy, Zod). Use when scaffolding application models, generating TypeScript data layers, or synchronizing schemas; for translating raw SQL across dialects, use transpile_sql_dialect instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'schema_ddl' ('orm_target' defaults to 'drizzle_orm_typescript'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

  Parameters:

  • schema_ddl (required) — string — Database schema DDL statements defining tables, primary keys, and relationships.
  • orm_target — string — Target ORM framework standard: Prisma schema, Drizzle ORM TypeScript, SQLAlchemy Python 2.0, or Zod types.
  • include_relations — boolean — Whether to generate explicit foreign key relation decorators and navigation properties.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.