safe-agent-mcp

Free MCP server that checks AI-agent code for guard patterns: idempotency keys, approval gates, API-key privilege audits. Static checks only — never executes your code.

GitHub

Documentation

Safe AI Agent — Guard Checks (free MCP server)

A free, read-only MCP server with three diagnostic tools for people who run AI agents in production. Distilled from the Safe AI Agent Pack — the production guard modules used by the Sage personal agent and the Growl AI marketing SaaS.

No network calls. No writes. Inputs that look like real secrets are refused.

Tools

ToolWhat it does
audit_api_keysFlags over-privileged API keys from their permission descriptions (never pass key values — secret-looking entries are rejected, not stored)
check_idempotency_patternScans a code snippet for the signals that actually stop duplicate execution: idempotency key, server-side store, uniqueness, short-circuit, payload binding, approval separation
explain_guard_patternExplains a production guard pattern — the failure it prevents and its minimal shape (idempotency_key, approval_gate, outbox, key_inventory, circuit_breaker, signed_approval_link)

Install & run

git clone <this repo>
cd safe-agent-mcp
python3 -m venv .venv && .venv/bin/pip install -r requirements.txt
.venv/bin/python safe_agent_mcp.py   # stdio transport

Claude Desktop / Cursor MCP config:

{
  "mcpServers": {
    "safe-agent-guard-checks": {
      "command": "/path/to/.venv/bin/python",
      "args": ["/path/to/safe_agent_mcp.py"]
    }
  }
}

Test

.venv/bin/python test_server.py   # in-memory client; calls every tool

The full pack

This free server is the diagnostic front door. The production modules — SQLite idempotency store, @once decorator, approval outbox with HMAC-signed approval links, the token-privilege inventory script, 18 regression tests and the 100 production-traps catalog — ship in the Safe AI Agent Pack ($69 / team $199).

License

MIT for this free server. The paid pack has its own commercial license.

Get the kit