Atomadic MCP

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

Atomadic MCP: 68 deterministic tools for agent identity, escrow, SLA, EU AI Act compliance.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Atomadic MCP": {
      "url": "https://mcp.atomadic.tech/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (68)

• murmuration

  START HERE (free, no key). Initialize your Atomadic control surface in one call: returns a verbose, step-by-step setup (SDK install, MCP connect, your unlocked tools), a RUNNABLE polyglot demo that proves the superpowers, recon links, and a one-command bootstrap. Idempotent — re-call anytime to re-check.

  Parameters:

  • agent_id — string — Optional stable id to track your onboarding state across calls.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• agents_contradiction

  [agents] Detect contradictions in agent outputs

  Parameters:

  • statements (required) — array

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• agents_intent_classify

  [agents] Agent intent classification

  Parameters:

  • text (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• agents_plan

  [agents] Autonomous agent goal planning

  Parameters:

  • goal (required) — string
  • constraints — object — Optional constraints for the plan (e.g., time limits, resource caps)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• agents_register

  [agents] Register an agent

  Parameters:

  • agent_id (required) — string
  • capabilities (required) — array

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• agents_reputation

  [agents] Agent reputation and trust score

  Parameters:

  • agent_id (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• agents_semantic_diff

  [agents] Semantic diff between agent outputs

  Parameters:

  • output_a (required) — string
  • output_b (required) — string
  • context — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• agents_topology

  [agents] Live swarm topology

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• compliance_check

  [security] GDPR/CCPA compliance gate

  Parameters:

  • data_type (required) — string
  • jurisdiction (required) — string
  • operation (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• compliance_eu_ai_act

  [security] EU AI Act compliance certificate

  Parameters:

  • system_id (required) — string
  • risk_category (required) — string
  • intended_purpose (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• compliance_explain

  [security] Explainability certificate (XPL-100-ExplainBound)

  Parameters:

  • model_id (required) — string
  • decision_id (required) — string
  • subject_context (required) — object

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• compliance_fairness

  [security] Fairness proof (FNS-100-FairnessBound)

  Parameters:

  • model_id (required) — string
  • dataset_id (required) — string
  • protected_attrs (required) — array
  • metric (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• compliance_incident

  [security] Report compliance incident

  Parameters:

  • system_id (required) — string
  • severity (required) — string
  • description (required) — string
  • affected_users (required) — integer

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• compliance_incidents

  [security] Incident registry

  Parameters:

  • system_id (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• compliance_lineage

  [security] Data lineage (LIN-100-ChainIntegrity)

  Parameters:

  • model_id (required) — string
  • dataset_stages (required) — array

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• compliance_oversight

  [security] Log oversight event

  Parameters:

  • system_id (required) — string
  • reviewer_id (required) — string
  • decision (required) — string
  • notes (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• compliance_oversight_history

  [security] Oversight history

  Parameters:

  • system_id (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• compliance_transparency

  [security] Transparency report

  Parameters:

  • system_id (required) — string
  • period (required) — string
  • include (required) — array

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• defi_bridge_verify

  [defi] Bridge Proof (BRP-100-BridgeIntegrity)

  Parameters:

  • bridge_id (required) — string
  • source_chain (required) — string
  • dest_chain (required) — string
  • amount (required) — number
  • token (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• defi_contract_audit

  [defi] Contract Verify (CVR-100-AuditBound)

  Parameters:

  • contract_id (required) — string
  • contract_type (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• defi_liquidation_check

  [defi] Liquid Shield (LQS-100-LiquidationBound)

  Parameters:

  • position_id (required) — string
  • collateral_value (required) — number
  • debt_value (required) — number
  • collateral_factor (required) — number

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• defi_optimize

  [defi] LP parameter optimization (DFP-100-OptimalTick)

  Parameters:

  • protocol (required) — string
  • position (required) — object
  • risk_tolerance (required) — number

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• defi_oracle_verify

  [defi] Oracle guard (OGD-100-ManipulationBound)

  Parameters:

  • oracle_address (required) — string
  • price_feed (required) — string
  • reference_price (required) — number
  • asset (required) — string
  • tvl_at_risk (required) — number

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• defi_risk_score

  [defi] DeFi risk scoring (DFI-101-RiskScoreBound)

  Parameters:

  • protocol (required) — string
  • position (required) — object
  • market_conditions (required) — object

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• defi_yield_optimize

  [defi] Yield Oracle (YLD-100-YieldConvergence)

  Parameters:

  • principal_usd (required) — number
  • risk_tolerance (required) — number

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• drift_certificate

  [trust] Drift certificate

  Parameters:

  • id (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• drift_check

  [trust] DriftGuard check (DRG-100-DriftBound)

  Parameters:

  • model_id (required) — string
  • reference_window (required) — object
  • current_window (required) — object

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• escrow_create

  [defi] Create agent-to-agent escrow

  Parameters:

  • payer_id (required) — string
  • payee_id (required) — string
  • amount (required) — number
  • currency (required) — string
  • conditions — object

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• escrow_dispute

  [defi] Open escrow dispute

  Parameters:

  • escrow_id (required) — string
  • reason (required) — string
  • evidence — object

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• escrow_release

  [defi] Release escrowed funds

  Parameters:

  • escrow_id (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• forge_badge_{model}

  [fuse] Model quality badge

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• forge_delta_submit

  [fuse] Submit a model delta

  Parameters:

  • model_id (required) — string
  • delta (required) — object
  • description — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• forge_leaderboard

  [fuse] Model leaderboard

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• forge_quarantine

  [fuse] Quarantined models

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• forge_verify

  [fuse] Verify a model submission

  Parameters:

  • model_id (required) — string
  • verification_type — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• identity_sybil_check

  [identity] Sybil-resistance check

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• identity_verify

  [identity] Topological identity verification

  Parameters:

  • agent_id (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• inference

  [inference] Chat inference with hallucination guard

  Parameters:

  • messages (required) — array

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• inference_stream

  [inference] Streaming inference with chain-of-thought

  Parameters:

  • messages (required) — array

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• oracle_entropy

  [trust] Entropy epoch oracle

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• oracle_hallucination

  [trust] Hallucination oracle

  Parameters:

  • claim (required) — string
  • context — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• rag_augment

  [inference] Trusted RAG augmentation

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• ratchet_advance

  [identity] RatchetGate — advance session

  Parameters:

  • session_id (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• ratchet_probe

  [identity] RatchetGate — health probe

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• ratchet_register

  [identity] RatchetGate — register session

  Parameters:

  • session_id (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• reputation_record

  [agents] Record agent interaction

  Parameters:

  • agent_id (required) — string
  • interaction_type (required) — string
  • outcome (required) — string
  • counterparty_id — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• rng_quantum

  [inference] Quantum random number with proof

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• rng_verify

  [inference] Verify current epoch random value

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• security_zero_day

  [security] Zero-day threat assessment

  Parameters:

  • target (required) — string
  • context — object

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• sla_register

  [agents] Register an SLA

  Parameters:

  • provider_id (required) — string
  • consumer_id (required) — string
  • terms (required) — object

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• sla_report

  [agents] Report SLA violation

  Parameters:

  • sla_id (required) — string
  • violation_type (required) — string
  • description — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• swarm_inbox

  [agents] Poll swarm inbox

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• swarm_relay

  [agents] Relay message through swarm

  Parameters:

  • target_agent_id (required) — string
  • message (required) — object
  • ttl — integer — Hop limit for relay

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• text_keywords

  [inference] Keyword extraction

  Parameters:

  • text (required) — string
  • max_keywords — integer

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• text_sentiment

  [inference] Sentiment analysis

  Parameters:

  • text (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• text_summarize

  [inference] Text summarization

  Parameters:

  • text (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• threat_score

  [security] Multi-vector threat score

  Parameters:

  • agent_id (required) — string
  • context — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• trust_decay

  [trust] Current trust ceiling value

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• trust_history

  [trust] Trust score history

  Parameters:

  • agent_id (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• trust_score

  [trust] Bounded trust score

  Parameters:

  • agent_id (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• audit_work_claim

  [Ledger product, entitlement: ledger] Recompute-audit an agent work claim: re-derive a deterministic SHA-256 digest from the claimed inputs and check it against the claimed digest. Returns GREEN (matches), RED (tampered), or UNVERIFIED (no claim supplied). Replay, not opinion. 3 free calls/day, then entitlement 'ledger'.

  Parameters:

  • inputs (required) — object — The work/claim payload to recompute a digest over.
  • claimed_digest — string — The agent's claimed SHA-256 digest to verify against. Omit for UNVERIFIED + the recomputed digest.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• verify_settlement

  [Ledger product, entitlement: ledger] Proof-gated settlement: recompute the work digest and authorize a payout only if the claimed digest verifies GREEN. No proof, no payout. 3 free calls/day, then entitlement 'ledger'.

  Parameters:

  • inputs (required) — object — The work payload backing the settlement.
  • claimed_digest — string — Claimed digest the payout is conditioned on.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• receipt_reputation

  [Ledger product, entitlement: ledger] Compute an agent's reputation from a ledger of verifiable receipts (verified minus refuted), deterministically - not from vibes or LLM judgment. 3 free calls/day, then entitlement 'ledger'.

  Parameters:

  • receipts (required) — array — List of receipt objects, each with an 'ok' boolean and optional 'score'.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• detect_contradiction

  [Ledger product, entitlement: ledger] Detect contradictions across structured claims: the same key asserted with conflicting values flips RED, otherwise GREEN. Deterministic and recomputable. 3 free calls/day, then entitlement 'ledger'.

  Parameters:

  • claims (required) — array — List of claim objects, each with a 'key' (or 'subject') and a 'value'.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• enforce_sla

  [Ledger product, entitlement: ledger] Enforce an SLA/obligation by recomputation: the obligation is met only if the work verifies GREEN against its claimed digest. 3 free calls/day, then entitlement 'ledger'.

  Parameters:

  • inputs (required) — object — The work payload to verify.
  • obligation — string — Human-readable obligation label.
  • claimed_digest — string — Claimed digest the obligation is conditioned on.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• route_capability

  [Ledger product, entitlement: ledger] Route a natural-language intent to a deterministic capability/pipeline coordinate. 3 free calls/day, then entitlement 'ledger'.

  Parameters:

  • intent (required) — string — The natural-language intent to route.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• render_polyglot_roundtrip_pure

  [Fuse product · entitlement: fuse · FREE_R2_DEMO] Syntax-as-Data polyglot render head: source -> language-neutral logic IR -> source in target language. Canonical demo examples baked to R2 (4 examples × 12 languages). Live emit of novel inputs via the SDK.

  Parameters:

  • source_text (required) — string
  • atom_name (required) — string
  • language — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• render_polyglot_all_pure

  [Fuse product · entitlement: fuse · FREE_R2_DEMO] Polyglot emit to all 7 supported targets in one call. Returns {ok, ir, results, languages}. Canonical demo examples baked to R2; novel inputs via SDK.

  Parameters:

  • source_text (required) — string
  • atom_name (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website

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