trust-gate-mcp

Post-quantum, tamper-evident receipts for consequential agent actions, as an MCP server.

Seven tools, one shared signing primitive: the open-sourceOpenAgentOntologymint_receipt.

PQ-required verify (the default) demandsat least oneverified post-quantum leg, so the dual-leg default is a real post-quantum posture, not a downgrade -- but only the[slh]install gives you the hash-based third leg.

Quantum Hardening (pol.must_do.150 reference implementation)

- H1key persistence + bootstrap with FAIL-CLOSED kid-drift check
- H2per-IP token-bucket rate limit (DoS-hardened: FIFO eviction + body cap)
- H3PQ-required verify (defeats signature-stripping downgrade attacks)
- H4128-bitkidon every minted receipt (offline same-notary check)
- Optional bearer-auth toggle + narrowed CORS viaTRUST_GATE_BEARER_TOKEN+TRUST_GATE_ALLOWED_ORIGINS
- 33/33 tests including adversarial PQ-strip + IP-rotation attack simulations

SeePUBLISH.mdfor the full hardening status table.

pip install trust-gate-mcp trust-gate-mcp

Add[slh]for the hash-based third leg. From a checkout,pip install -e ".[dev]"thenpython -m trust_gate_mcp.

Container deploy (Smithery / any container host)

docker build -t trust-gate-mcp . docker run -p 8081:8081 -v trust-gate-data:/data/oao trust-gate-mcp

The volume mount on/data/oaoisrequired for production-- without it the signing key rotates per restart and breaks long-running verification chains. The persistentkey_metadata.jsonholds the notary'skid; the bootstrap step refuses to start if it drifts.

Verify HMAC-signed compliance attestations from any MEOK MCP server — checks cryptographic signatures, validates timestamps, and produces verifiable trust chains for AI compliance audits.

Deterministic AI-liability attribution — signed, Bitcoin-anchored certificates that compute vendor/deployer/user fault splits for AI incidents. No LLMs, byte-identical reproducible.

KHEPRA MCP Server smithery badge MCP Registry License Container PQC Sovereign compliance engine with 36,195 STIG/CCI/NIST/CMMC mappings. Air-gappable. Zero token costs. Run ert_scan → get a Godfather Report with dollar-denominated business impact. The only MCP compliance server that runs on your metal — with the World's First DoD PQC STIG built in. PQC-01-STIG-V1R1 — Full Whitepaper → 17 controls covering CNSA 2.0, FIPS 203/204/205, and the NSA's May 2026 MCP security advisory. The world's first DoD-style Post-Quantum Cryptography STIG, including the first PQC controls for agentic AI and MCP deployments.

Comprehensive audit logging for agent-to-agent interactions — immutable event trails, tamper-evident hashing, structured log export (SIEM-compatible), and compliance-grade retention for regulated industries.

Cryptographic runtime governance for AI agents. 20 tools. Sealed policy artifacts, continuous measurement, tamper-evident proof. Ed25519 + SHA-256.

AI Agent Supply Chain Security - Intercepts and validates every package installation, git clone, and script download triggered by AI coding agents before it executes.

AI Bill of Materials generation — model cards, dataset provenance, supply chain transparency, CycloneDX format by MEOK AI Labs

Structured AI incident reporting for EU AI Act Article 62 — generates mandatory incident reports, severity classification, root cause analysis, and regulator-ready submissions for serious AI incidents.

AI incident detection, classification, and regulatory reporting — covers EU AI Act Article 62, NIST AI RMF, and OECD frameworks

Enforces organisational AI usage policies at the agent layer — blocks prohibited model calls, enforces data residency rules, logs policy violations, and ensures AI governance policies are machine-executable.