@complyedge/mcp

@complyedge/mcp

EU AI Act Article 5 and Article 50 runtime deny via TrustLint, offline. Classifiers (eu-ai-act-*) score the system; this server denies this prompt or output. Article 50 here is unlabeled or deceptive use, not C2PA.

npx -y @complyedge/mcp
pip install 'complyedge[mcp]'
pip install complyedge
pip install trustlint
claude mcp add complyedge -- npx -y @complyedge/mcp

Run offline TrustLint checks from any MCP host with Node.js:

{
  "complyedge": {
    "command": "npx",
    "args": ["-y", "@complyedge/mcp"]
  }
}

Tools

The server exposes three read-only tools.

Tool	Returns	Notes
check_compliance	PASS / FAIL with cited findings	Checks already-produced text. Optional jurisdiction: EU, US, GLOBAL
scan_prompt	SAFE / RISK_DETECTED	Checks a candidate prompt before it is sent to a model
list_rules	Rule inventory	Discovery only — does not evaluate text

Limitations and honest scope

• Tier-1 regex matching over a bundled YAML corpus. It does not evaluate Rego, and it is not the hosted runtime enforcement path — use @complyedge/sdk for POST /v1/check and the Article 12 audit trail.
• Findings are technical compliance evidence, not legal advice, not a legal opinion, and not a regulatory classification of an AI system.
• The corpus is bundled at build time. It is current as of the release you install, not a live regulatory feed.
• Read-only and local. No tool writes, sends, or persists anything, and the server makes no network calls and needs no API key.

Links

• @complyedge/sdk — hosted runtime enforcement and the Article 12 audit trail
• trustlint — the same offline engine as a CLI
• complyedge on PyPI — Python MCP server, published under this same registry entry
• GitHub Action: uses: complyedge/trustlint-action@v1
• GOPAL is an OPA library in your process. ComplyEdge is per-request deny + citation + trust page + MCP.
• trustlint on PyPI — Python linter
• Documentation · Trust portal