TrustAtom MCP Server
The TrustAtom MCP Server provides cryptographic signing, verification, querying, and compliance reporting for AI decisions:
Sign AI decisions (
create_trustatom): Cryptographically sign any AI decision (e.g.,APPROVE_LOAN,TRIAGE_PATIENT,DEPLOY) using Ed25519 + SHA-256 in under 3ms, producing a tamper-proof receipt with optionalcontext,risk_score(0.0–1.0), and auto-mapped compliance tags.Verify receipts (
verify_trustatom): Confirm the authenticity and integrity of an existing receipt by checking its Ed25519 signature and detecting any tampering.Query the receipt ledger (
query_receipts): Retrieve stored receipts filtered byactor,action,decisionoutcome (ALLOW/DENY), orlimit— useful for audits.Generate compliance reports (
get_compliance_report): Aggregate receipts into framework-mapped reports (HIPAA, SOX, NIST, SOC2, CMMC, ISO27001) suitable for board reporting or Authorization to Operate (ATO) packages.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@TrustAtom MCP Server Sign this clinical triage decision for HIPAA compliance"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
TrustAtom MCP Server
⚠️ Superseded by trust-gate-mcp
This repository is no longer the recommended way to mint Trust Gate receipts. It is kept public as a reference implementation and for historical context.
Use
trust-gate-mcpinstead:pip install trust-gate-mcp
This repo
trust-gate-mcpSigning
Ed25519 only
Ed25519 + ML-DSA-65 (FIPS 204), + SLH-DSA with liboqs
Tools
4
7
Receipt
envalways
SANDBOXreflects real environment
Published
no —
@cwn/trustatom-mcpwas never released to npmyes, on PyPI
Hosted
—
Maintained
no
yes
The
npx/npm installinstructions below therefore only work from a git clone. There is no@cwn/trustatom-mcppackage on the npm registry.
Cryptographic receipts for AI decisions. 5 minutes to your first receipt.
Every AI decision in your org is unsigned — and your auditor is going to ask about it. TrustAtom signs every decision with Ed25519 and returns a verifiable receipt in under 3ms.
Related MCP server: DCL Evaluator
Quick Start
git clone https://github.com/CWNApps/trustatom-mcp
cd trustatom-mcp
npm install
npm run keygen # Generate Ed25519 key pair
npm test # Run 8 eval testsAdd to Claude Desktop
{
"mcpServers": {
"trustatom": {
"command": "npx",
"args": ["tsx", "src/server.ts"],
"cwd": "/path/to/trustatom-mcp",
"env": { "TRUSTATOM_KEY_PATH": "./keys/trustatom_keys.json" }
}
}
}Then in Claude: "Sign this AI decision with TrustAtom" → receipt issued automatically.
What It Does
Tool | Description | When |
| Sign a decision, return receipt | At every AI decision point |
| Verify an existing receipt | During audit, dispute resolution |
| Query the receipt ledger | Compliance reporting |
| Framework-mapped report | Board report, ATO package |
Example: Healthcare AI Triage (HIPAA)
You: "Our clinical AI just triaged patient #4422 as ESI-3 with 67% confidence.
Sign this decision for HIPAA compliance."
Claude (via TrustAtom MCP):
✅ Receipt ta_7f3a2b signed in 1.2ms
Action: TRIAGE_PATIENT
Decision: ALLOW
Compliance: HIPAA:164.312(b), HL7
Risk Score: 0.80
Signature: ed25519:abc123...What the auditor sees: "On Mar 7 at 14:22, clinical-ai-v2 classified patient #4422 as ESI-3. Receipt ta_7f3a2b is Ed25519-signed. Control: HIPAA 164.312(b)."
Compliance Frameworks
TrustAtom auto-maps actions to framework controls:
Action | Frameworks |
| HIPAA 164.312(b), HL7 |
| SOX 302, FCRA |
| SOX 302, SEC 17a-4 |
| NIST PR, SOC2 CC6.1 |
| NIST PR/RS, SOC2 A1.2 |
Custom | NIST PR (default) |
Performance
Signing: <3ms average (Ed25519 + SHA-256)
Verification: <1ms
Receipt size: ~500 bytes JSON
Architecture
Your AI Agent
↓ (MCP call)
TrustAtom MCP Server (local)
├── Ed25519 key pair (you own the keys)
├── SHA-256 evidence hash
├── Compliance auto-mapping
└── In-memory ledger (pluggable to Neo4j/SQLite)
↓
Receipt returned to your agentEval Tests
8 tests covering signing, verification, tampering detection, compliance mapping, risk scoring, and performance:
npm test
# ✅ Signs a decision and returns a valid receipt
# ✅ Verifies an authentic receipt
# ✅ Detects tampered receipt
# ✅ Auto-maps TRIAGE_PATIENT to HIPAA compliance tags
# ✅ Auto-maps APPROVE_LOAN to SOX compliance tags
# ✅ Computes risk score from action when not provided
# ✅ Signs DENY decisions with same integrity
# ✅ Signs within 3ms target for production use
# Results: 8 passed, 0 failedEnterprise
Need hosted infrastructure with SLA? Contact hello@cyberwarriornetwork.com
Tier | Calls/day | Price |
Developer | 1,000 | Free |
Professional | 100,000 | $299/mo |
Enterprise | Unlimited | $2,499/mo |
Built By
Cyber Warrior Network — Trust Gate: Policy-gated AI decisions with cryptographic receipts.
No Receipt. No Trust.
Available Tools
4 toolscreate_trustatomA
Sign an AI decision and return a cryptographic receipt. Every AI decision that matters should have a receipt. Signing takes <3ms. Receipt is Ed25519-signed + SHA-256-hashed.
Inputs: actor (required), action (required), decision (required), context, +2 more.
get_compliance_reportC
Generate a compliance report mapped to a specific framework. Aggregates all receipts tagged with the specified framework.
Inputs: framework (required).
query_receiptsC
Query the receipt ledger for audit or compliance reporting. Filter by time range, action, actor, or decision.
Inputs: actor, limit, action, decision.
verify_trustatomB
Verify the integrity of an existing TrustAtom receipt. Confirms the Ed25519 signature is authentic and the receipt hasn't been tampered with.
Inputs: receipt_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose with no overlap: create_trustatom signs decisions, get_compliance_report generates reports, query_receipts searches the ledger, and verify_trustatom validates receipts. The descriptions clearly differentiate their functions, eliminating any ambiguity.
All tool names follow a consistent verb_noun pattern (create_trustatom, get_compliance_report, query_receipts, verify_trustatom), using snake_case throughout. This predictability makes the tool set easy to navigate and understand.
With 4 tools, this server is well-scoped for its purpose of cryptographic receipt management and compliance. Each tool serves a distinct role in the lifecycle (create, query, report, verify), and the count is neither too sparse nor bloated.
The tool set provides complete coverage for the domain of AI decision receipt management: create_trustatom handles creation, query_receipts enables retrieval, get_compliance_report supports reporting, and verify_trustatom ensures integrity. No obvious gaps exist for core workflows.
Maintenance
Related MCP Connectors
Tamper-evident SHA-256 hash-chained decision notary for EU AI Act, NIST AI RMF & SOC2.
Governed AI actions with signed, verifiable receipts: free keyless reads, human-approved writes.
Runtime AI governance: decision gates, human approval, hash-chained audit, compliance mapping.
Register every AI agent, log every action, prove it. EU AI Act compliance built in.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI agents to sign decisions with post-quantum cryptographic proofs and maintain secure audit trails for compliance. It provides tools for stamping events, verifying chain integrity, and exporting audit data across industries like finance and healthcare.481 npmMIT
- FlicenseNot gradedqualityFmaintenanceSuperseded. Earlier version of the DCL product (MCP endpoint at /sse with API key, plus an offline desktop audit trail). Not the current path for agents. Use the hosted DCL Trust Oracle: https://github.com/Fronesis-Labs/dcl-webhook (MCP endpoint https://mcp.fronesislabs.com/mcp, Streamable HTTP, x402 payment, no API key).-
- AlicenseBqualityCmaintenanceEnables AI compliance attestation and verification for EU AI Act, HIPAA, and other regulations, with tools for signing, proving, and anchoring AI decisions to Hedera mainnet.14561 npm1Apache 2.0
- AlicenseBqualityBmaintenanceSigned receipts for agent actions and a read-only-allowlist decision gate, as an MCP server. Ed25519, plus ML-DSA-65 when the post-quantum backend is available. gate_decision returns ALLOW, DENY or ESCALATE from action names and does not observe or block anything. verify_receipt takes expected_kid to pin which key signed. Seven tools.16Apache 2.0