{
  "markdown": "# Guardrail MCP\n\nSmall, free, read-only Remote MCP for deterministic action preflight.\n\nIt exposes two tools:\n\n- `get_guardrail_capabilities`\n- `assess_action_risk`\n\nThe check detects a deliberately small set of high-risk patterns: credential exposure, fund movement, external writes, and instruction overrides. It does not execute an action, persist a request, authenticate a user, charge a payment, call AI, or fetch external URLs.\n\n## Local use\n\n```bash\nnpm run check\nnpm test\nnpm run dev\n```\n\nEndpoints: `GET /`, `GET /health`, and stateless Streamable HTTP `POST /mcp`.\n\n## Boundary\n\nThis is an informational deterministic preflight, not a safety guarantee or legal, financial, or security advice. Deployment and any public endpoint require separate approval.\n",
  "bytes": 765,
  "sha": "33b2bf1fa7e0024f9dfc354d5ca7155fec084e879e4fb46a0f818fe99804771b",
  "repo_slug": "kadopi/guardrail-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_kadopi_guardrail_mcp_19804e97/readme"
}