Tresslers Intelligence MCP Server

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

Sovereign intelligence dossiers, daily briefings, RAG search, knowledge graph, codon optimizer.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Tresslers Intelligence MCP Server": {
      "url": "https://tresslersgroup.com/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (12)

• list_dossiers

  Returns a list of all available intelligence dossier slugs.

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

• read_dossier

  Reads the pure text contents of a specific intelligence dossier. Requires x402 payment proof for premium intelligence. Without payment proof, returns a high-fidelity strategic excerpt and payment challenge.

  Parameters:

  • slug (required) — string — The slug of the dossier to read (e.g., 'sovereign-ai-state-national-policy-2026').
  • payment_proof — string — Standard x402 signed USDC transaction proof (0x...). Required for full decrypted access.

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

• search_intelligence_matrix

  Executes a semantic vector similarity search across the entire ThinkForge intelligence substrate. Returns relevant snippets and strategic conviction metadata.

  Parameters:

  • query (required) — string — Semantic research question (e.g., 'What are the geopolitical vulnerabilities in green hydrogen supply chains?').
  • limit — number — Max results to return (default 5, max 10).
  • filter — string — Optional SQL-like metadata filter (e.g., 'convictionScore >= 0.85').

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

• query_knowledge_graph

  Traverses the multi-hop conceptual knowledge graph across entities (GraphRAG). Free preview available for direct 1-hop adjacencies. Deeper reasoning (2-3 hops) requires x402 settlement.

  Parameters:

  • entity_id (required) — string — Target conceptual entity or dossier slug (e.g., 'Quantum AI', 'ThinkForge').
  • depth — number — Graph traversal hop depth (1 for free preview, 2 to 3 for deep reasoning).
  • payment_proof — string — Standard x402 signed USDC transaction proof (0x...). Required for multi-hop graph access.

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

• get_dossier_delta

  Queries intelligence updates and conviction deltas attested since a specific UTC timestamp.

  Parameters:

  • since_timestamp (required) — string — ISO UTC timestamp (e.g., '2026-05-01T00:00:00Z').

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

• ask_intelligence_rag

  Ask a natural-language question and receive structured intelligence context retrieved from Tresslers Group dossiers via RAG (Retrieval Augmented Generation). Returns relevant document chunks, source citations, conviction metadata, and graph neighborhood data. The calling LLM should synthesize the returned context into a coherent answer.

  Parameters:

  • question (required) — string — Natural language question (e.g., 'What are the key geopolitical risks in sovereign AI policy?').
  • max_sources — number — Maximum number of source dossier chunks to retrieve (default 5, max 8).

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

• batch_optimize_codon

  Batch codon optimization for teams and agents: optimize up to 50 protein or cDNA coding sequences in one call with the Logos bio-engine (CAI maximization, GC harmonization, restriction-site avoidance, consensus leaders). Free tier: 100 sequences per caller per day. Overage is $0.50 USDC per 10 sequences ($0.05/sequence) on Base, verified on-chain — pass payment_proof when the batch exceeds the free tier. Research Use Only (RUO); select-agent sequences prohibited.

  Parameters:

  • sequences (required) — array — Amino acid sequences (single-letter uppercase) or DNA coding sequences to optimize. Max 50 per call; max 5000 characters each.
  • host — string — Target expression organism: 'e_coli', 'h_sapiens' (HEK293), 'c_griseus' (CHO), 's_cerevisiae', 'p_pastoris', 'v_natriegens', 'n_benthamiana', 'a_thaliana'. Default: 'e_coli'
  • api_key — string — Optional stable caller identifier for quota tracking (useful behind shared IPs). Self-asserted in v1.
  • gc_target — number — Target global GC percentage (e.g., 52 for E. coli, 58 for Human). Optional.
  • payment_proof — string — USDC transaction hash on Base. Required when the batch exceeds the 100/day free tier.

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

• optimize_codon

  Optimizes a protein (amino acid) or cDNA coding sequence for maximal recombinant expression yield in a target host organism using the Logos biocomputing engine. Executes Codon Adaptation Index (CAI) maximization, GC-content harmonization, restriction site avoidance, and ribosomal consensus leader generation. Research Use Only (RUO). In-silico modeling only; select-agent and regulated pathogen sequence optimization is strictly prohibited under 42 CFR 73 and BWC compliance. Free and open to all AI agents.

  Parameters:

  • sequence (required) — string — Amino acid sequence (single-letter uppercase e.g. 'MSKGEELFT...') or DNA coding sequence to optimize.
  • host — string — Target expression organism: 'e_coli', 'h_sapiens' (HEK293), 'c_griseus' (CHO), 's_cerevisiae', 'p_pastoris', 'v_natriegens', 'n_benthamiana', 'a_thaliana'. Default: 'e_coli'
  • gc_target — number — Target global GC percentage (e.g., 52 for E. coli, 58 for Human). Optional.

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

• get_model_record

  Queries the public calibration and backtest ledger of Tresslers Group sovereign intelligence models. Supports filtering by settlement type ('contract_settled' for live prediction markets, 'outcome_tracked' for internal foresight models, 'unscored_archive' for pre-commitment history, or 'all'). Returns Brier calibration scores, transparent failure analysis, and verifiable primary source URLs.

  Parameters:

  • status — string — Filter by resolution status (default: 'ALL').
  • category — string — Optional filter by intelligence pillar/category.
  • settlement_type — string — Filter by settlement tier: 'contract_settled' (live prediction market order-books), 'outcome_tracked' (internal Bayesian foresight), 'unscored_archive' (pre-commitment era), or 'all' (default).

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

• search_dossiers

  Searches and filters across all published Tresslers Group intelligence dossiers by keywords, strategic domain/category, tags, or conviction threshold.

  Parameters:

  • query (required) — string — Search query or keywords to match across title, excerpt, content, and tags.
  • tag — string — Optional tag filter (e.g., 'sovereign-ai', 'energy-transition').
  • limit — number — Maximum number of dossiers to return (default: 5, max: 20).
  • category — string — Optional category filter (e.g., 'Geopolitics & Sovereign Policy', 'Energy & Infrastructure').
  • min_conviction — number — Minimum conviction threshold (0.0 to 1.0, e.g., 0.85).

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

• verify_commitment

  Cryptographically verifies a predictive alpha pre-commitment against the immutable SHA-256 ledger using either a 64-character hash digest or canonical preimage parameters.

  Parameters:

  • hash — string — 64-character lowercase hexadecimal SHA-256 commitment digest.
  • preimage — string — Full pipe-delimited UTF-8 canonical preimage string (YYYY-MM-DD|question|model_odds|target_dossier_slug).
  • model_odds — number — Model odds integer component (0-100).
  • dossier_slug — string — Target dossier slug component.
  • dispatch_date — string — Dispatch date component (YYYY-MM-DD).
  • market_question — string — Exact market question component.
  • canonical_preimage — string — Alternative key for canonical preimage string.

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

• get_alpha_gap

  Retrieves prediction market Alpha Gaps comparing Tresslers Group Bayesian model odds against Polymarket order books, along with Brier scores, calibration alpha (+3,480 bps benchmark), and cryptographic SHA-256 pre-commitments.

  Parameters:

  • limit — number — Maximum number of Alpha Gap records to return.
  • status — string — Filter by status or settlement type (e.g., 'CONTRACT_SETTLED', 'OUTCOME_TRACKED', 'RESOLVED', 'PENDING', 'ALL').
  • category — string — Optional filter by strategic intelligence domain.
  • min_divergence — number — Minimum absolute divergence gap in percentage points (e.g. 20 for >= 20% gap).
  • settlement_type — string — Filter by settlement tier: 'contract_settled', 'outcome_tracked', 'unscored_archive', or 'all'.

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

Publisher website Repository

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