SkillTriage

Download one published package and run static analysis on its code with MoorAI's open-source engine. npm and PyPI packages also get ten MCP pre-install checks on their registry metadata, a reputation score and a known-compromised release check. Static analysis only: the package is never installed and the server is never run. Returns a verdict (CLEAN, CAUTION, REVIEW, DO-NOT-INSTALL or NAME-NOT-PUBLISHED), content-free findings (threat ids, categories, file paths, hashes; never file contents) and a permalink. The package name and version are sent to its registry. A completed analysis is reused for 24 hours; a new one can take a minute and runs one at a time.

{
  "type": "object",
  "properties": {
    "ref": {
      "type": "string",
      "maxLength": 300,
      "description": "npm:<name>[@version], pypi:<name>[==version] or github:<owner>/<repo>/<path>[@ref] (a folder, not a whole repository)"
    }
  },
  "required": [
    "ref"
  ],
  "additionalProperties": false
}

Check a pasted MCP client config (.mcp.json, claude_desktop_config.json, mcp.json, Codex config.toml). Reports each npm or PyPI launch by its position and how its version is pinned (exact, @latest, a tag or range, none), flags releases on the known-compromised list, and runs static analysis over the text. Server names, package names, arguments, env and header values are never returned or stored; remove secrets before sending anyway. Static analysis only; nothing is run or fetched. Returns a verdict (CLEAN, CAUTION, REVIEW, DO-NOT-INSTALL or NAME-NOT-PUBLISHED), the pinning advice and a permalink.

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "maxLength": 1000000,
      "description": "The config file's text"
    },
    "filename": {
      "type": "string",
      "maxLength": 100,
      "description": "The config's filename, ending in .json or .toml (default .mcp.json)"
    }
  },
  "required": [
    "text"
  ],
  "additionalProperties": false
}

Scan one agent skill or instruction file (SKILL.md, AGENTS.md, a tool.json, any text file) with MoorAI's open-source engine. Static analysis only; nothing is run. The text is written to a temporary directory, scanned and deleted; only its hash, the verdict and content-free findings are kept. Returns a verdict (CLEAN, CAUTION, REVIEW, DO-NOT-INSTALL or NAME-NOT-PUBLISHED), the findings and a permalink.

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "maxLength": 1000000,
      "description": "The file's text"
    },
    "filename": {
      "type": "string",
      "maxLength": 100,
      "description": "The file's name, which sets how it is analysed (default SKILL.md)"
    }
  },
  "required": [
    "text"
  ],
  "additionalProperties": false
}

Look up the verdict the public catalogue has published for an MCP server package on npm or PyPI. Returns found:false when the catalogue has no published verdict for that name; that is not a clean result. Nothing is downloaded or scanned. This request names the package to the server; to match without naming it, download /api/reputation-feed.json and match on your side.

{
  "type": "object",
  "properties": {
    "ecosystem": {
      "type": "string",
      "enum": [
        "npm",
        "pypi"
      ],
      "description": "The package registry"
    },
    "name": {
      "type": "string",
      "maxLength": 214,
      "description": "The package name"
    },
    "version": {
      "type": "string",
      "maxLength": 100,
      "description": "Optional: the version you plan to install; the reply says whether the published verdict is for it"
    }
  },
  "required": [
    "ecosystem",
    "name"
  ],
  "additionalProperties": false
}