@humanaccepted/mcp
Provides tamper-evident receipt logging for tool calls made by OpenAI agents (e.g., GPT models) when used via MCP, supporting EU AI Act compliance.
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., "@@humanaccepted/mcp show me my session info"
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.
humanaccepted-mcp
MCP server that emits signed, EU AI Act Article 12-compliant receipts on every AI tool call.
Drop-in Model Context Protocol server. Every tools/call your agent makes — through Claude Desktop, Cursor, or any MCP-compatible host — is wrapped and emitted as a signed tool_call receipt into the HumanAccepted registry, chained to the previous receipt in the session, and verifiable offline against the public Python / TypeScript reference verifiers.
A single line of MCP config, no code changes, no host rewrites.
What it does
Sits in front of your agent's tool layer as a passthrough MCP server.
Wraps every
tools/callin abefore → afterpair of signed receipts:Start receipt (
kind: "tool_call",duration_ms: 0) — captures intent + inputs.End receipt — captures output + duration +
ok | error | timeout | deniedresult.
Chains both via
chain.prevso an auditor can replay the full session in order.Generates a stable
run_idper MCP session for end-to-end traceability.
All receipts are signed with the tenant's Ed25519 key inside the HumanAccepted Worker. The MCP server itself holds no private key material — it authenticates with Bearer sk_... and the Worker does the signing.
Related MCP server: agent-audit-trail
Quick start
# 1. Get an API key (one-time, returns a tenant + sk_…)
curl -X POST https://humanaccepted.ola-turmo.workers.dev/v1/bootstrap
# 2. Run the MCP server (npx pulls it from npm; no local install needed)
HUMANACCEPTED_API_KEY=sk_... \
npx -y @humanaccepted/mcpTo use it in Claude Desktop or Cursor, add this to your MCP config:
{
"mcpServers": {
"humanaccepted": {
"command": "npx",
"args": ["-y", "@humanaccepted/mcp"],
"env": {
"HUMANACCEPTED_API_KEY": "sk_...",
"HUMANACCEPTED_AGENT_ID": "my_agent",
"HUMANACCEPTED_AGENT_TYPE": "claude-sonnet-4.6"
}
}
}
}The server connects on stdio, prints [humanaccepted-mcp] Connected to … to stderr, and from that point every tool call your agent makes is recorded.
Configuration
Env var | Required | Default | Purpose |
| yes | — | Tenant |
| no |
| Override for staging / local Worker |
| no |
| Stable id across the session (good for dashboards) |
| no |
| e.g. |
What it exposes
This MCP server exposes one meta-tool:
humanaccepted_session_info— returns the current session'srun_id, last receipt id, base URL, agent id, and tenant key fingerprint. Useful for debugging and for letting downstream code correlate receipts to a session.
All other tools/call requests are passed through but wrapped: the upstream tool still runs as normal, and a tool_call receipt pair is emitted to HumanAccepted for each invocation.
Receipt shape
Receipts follow HumanAccepted spec v1.1 (kind: "tool_call" was added in v1.1). A minimal example of the before half:
{
"kind": "tool_call",
"version": 2,
"tenant": "ten_3K9F2X",
"id": "rcp_4PZ8QJ2M1X9Y7K0ABCDEF1234",
"issued_at": "2026-06-28T09:53:11.421Z",
"agent": {
"id": "my_agent",
"type": "claude-sonnet-4.6",
"run_id": "run_01HF3R8K2Q5P9X7Z4M6V0YJWBN"
},
"tool": {
"name": "get_weather",
"version": "1.0.0",
"input": { "city": "Oslo" },
"output": null,
"duration_ms": 0,
"result": "ok"
},
"chain": { "prev": null, "run_id": "run_01HF3R8K2Q5P9X7Z4M6V0YJWBN" },
"canonical": "ha:v1:tool_call:ten_3K9F2X:rcp_4PZ…:{…sorted-utf8-json…}",
"signature": {
"alg": "ed25519",
"key_id": "k_8N4Q",
"value": "7c3f…(ed25519 sig over canonical)"
}
}The after half repeats the same envelope with duration_ms > 0, the actual output, and chain.prev = rcp_4PZ… (the start receipt's id).
Verify offline:
# Python
python3 -m verifier.python.verify --receipt rcp_4PZ... --pubkey <tenant-ed25519-pub>
# TypeScript
npx @humanaccepted/verify --receipt rcp_4PZ... --pubkey <tenant-ed25519-pub>EU AI Act Article 12
Article 12 of the EU AI Act requires providers of high-risk AI systems to keep automatic, tamper-evident logs of every interaction over the system lifecycle. The deadline is 2 August 2026 — 35 days from today (2026-06-28).
HumanAccepted is the open primitive for Article 12. The MCP server here is the drop-in layer: any MCP-compatible agent — Claude Desktop, Cursor, Claude Code, your custom host — gets Article 12 logging with one block of MCP config and zero changes to the agent code.
After running your agent for any length of time, fetch the full session's receipts:
curl https://humanaccepted.ola-turmo.workers.dev/v1/article12-export \
-H "Authorization: Bearer $HUMANACCEPTED_API_KEY" \
| jq '.counts, (.receipts | length)'Or replay one session:
curl https://humanaccepted.ola-turmo.workers.dev/v1/runs/$RUN_ID \
-H "Authorization: Bearer $HUMANACCEPTED_API_KEY" \
| jq '.chain_valid, .count'Local development
The repo ships TypeScript source in src/ (entry: src/server.ts) and a built dist/ for npx.
git clone https://github.com/Ola-Turmo/humanaccepted-mcp
cd humanaccepted-mcp
# Workaround for openclaw-user npm issues on shared VPS:
npm install --prefix /tmp/mcp-dev --cache /tmp/mcp-dev/.npm-cache
NODE_PATH=/tmp/mcp-dev/node_modules node --import tsx src/server.tsOr build:
npm run build && npm startTests:
HUMANACCEPTED_API_KEY=sk_... \
HUMANACCEPTED_BASE_URL=http://127.0.0.1:8789 \
npm testRepo layout
Path | Purpose |
| MCP server implementation — wraps |
| Thin entrypoint ( |
| Built JS for |
| Boot + |
|
|
| ES2022, strict, outDir |
Related projects
Project | What it is |
Open spec v1.1 — receipt shapes, canonical form, verifiers in 5 languages | |
Host product — Worker + Pages app (PR #6 ships v0.3 with these receipt kinds) | |
Live Worker |
|
Live host product |
|
Landing page (this repo) |
|
License
Apache-2.0
Available Tools
1 toolhumanaccepted_session_infoA
Returns information about the current HumanAccepted session — run_id, receipt count, and the tenant's public key (for offline verification).
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of confusion or overlap. The tool's purpose is clearly defined and distinct by virtue of being the sole tool.
With a single tool, there is no pattern to violate. The name 'humanaccepted_session_info' is descriptive and follows a clear noun-based convention, which is internally consistent.
A single tool is on the thin side, but for a narrowly scoped server focused solely on session info, it is acceptable. The tool earns its place, though there is only one.
The tool fully covers the stated purpose of returning session information. Minor gaps could include related operations like verifying receipts, but within the narrow domain of 'session info' it is complete.
Maintenance
Related MCP Connectors
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
AI governance MCP server for EU AI Act compliance and jurisdiction verification
A paid remote MCP for CLI tool MCP, built to return verdicts, receipts, usage logs, and audit-ready
Verifiable execution records for AI agents: signed receipts, tamper-evident archives and portable evidence bundles, exposed via MCP and REST, with paid verify and anchor calls settled over x402.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server for AI compliance auditing. Scores agent outputs for hallucination liability under the EU AI Act, issues verifiable compliance stamps, and tracks audit history by agent.MIT
- AlicenseNot gradedqualityDmaintenanceMCP server providing immutable audit logging, policy enforcement, and compliance reporting for AI agent workflows, enabling regulatory compliance and chain integrity verification.1MIT
- FlicenseNot gradedqualityDmaintenanceA paid, hosted MCP server that acts as a witness layer for AI agent tool calls, providing receipt creation, approval evidence, argument redaction, result summaries, and audit exports.-
- AlicenseNot gradedqualityCmaintenanceAn MCP server that provides append-only, tamper-evident local receipts for AI agent actions, capturing command executions, outputs, and handoff evidence.MIT