SkillTriage MCP

SkillTriage is a static analysis service that scans AI agent skills, MCP server packages, and configuration files for security risks and compatibility issues before installation. It provides verdicts, findings, and pinning advice without executing code, ensuring safety through content-free analysis in a temporary environment.

Visit MoorAI

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by MoorAI

MCP endpoint (Streamable HTTP)

https://skilltriage.moorai.dev/mcp

Vendor documentation

What you can do with it

Scan MCP server packages for pre-install checks
Analyze MCP configuration files for security risks
Verify published package verdicts via ecosystem lookup
Scan AI agent skill definitions for safety

Source and maintenance

Vendor evidenceRegistry 0.6.1

mcp-registry: dev.moorai/skilltriage@0.6.1 Project website

Protocol and capabilities

Server: SkillTriage 0.7.0
MCP protocol: 2025-06-18
Tools: 4 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Checks MCP servers and agent skills before they are installed, with static analysis only: nothing is installed or run. scan_package downloads one published npm, PyPI or GitHub package and analyses its code (npm and PyPI also get ten MCP pre-install checks); scan_mcp_config checks a pasted MCP client config for unpinned or known-compromised launches; scan_skill scans one skill file; lookup_verdict returns the public catalogue's published verdict for a package. Submitted text is not stored: only a hash, the verdict and content-free findings. Calls are rate-limited per IP address.

Tools

4 advertised

scan_package — Scan an MCP server or skill package

Advertised by the server during the last successful anonymous check.

Advertised read-onlyOpen-world

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.

scan_package input schema

{
  "type": "object",
  "required": [
    "ref"
  ],
  "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)"
    }
  },
  "additionalProperties": false
}

scan_package annotations

{
  "title": "Scan a package",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

scan_mcp_config — Check an MCP client config

Advertised by the server during the last successful anonymous check.

Advertised read-only

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.

scan_mcp_config input schema

{
  "type": "object",
  "required": [
    "text"
  ],
  "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)"
    }
  },
  "additionalProperties": false
}

scan_mcp_config annotations

{
  "title": "Check an MCP config",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

scan_skill — Scan an agent skill file

Advertised by the server during the last successful anonymous check.

Advertised read-only

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.

scan_skill input schema

{
  "type": "object",
  "required": [
    "text"
  ],
  "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)"
    }
  },
  "additionalProperties": false
}

scan_skill annotations

{
  "title": "Scan a skill file",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

lookup_verdict — Look up a published MCP server verdict

Advertised by the server during the last successful anonymous check.

Advertised read-only

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.

lookup_verdict input schema

{
  "type": "object",
  "required": [
    "ecosystem",
    "name"
  ],
  "properties": {
    "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"
    },
    "ecosystem": {
      "enum": [
        "npm",
        "pypi"
      ],
      "type": "string",
      "description": "The package registry"
    }
  },
  "additionalProperties": false
}

lookup_verdict annotations

{
  "title": "Look up a verdict",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 360 ms
95th percentile latency: 360 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 1, 2026, 8:53 AM UTC · probe · passed · 360 ms · metadata changed · 4 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http skilltriage-mcp https://skilltriage.moorai.dev/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add skilltriage-mcp --url https://skilltriage.moorai.dev/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable skilltriage-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "skilltriage-mcp": {
      "url": "https://skilltriage.moorai.dev/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "skilltriage-mcp": {
      "type": "streamableHttp",
      "url": "https://skilltriage.moorai.dev/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start skilltriage-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "skilltriage-mcp": {
      "type": "http",
      "url": "https://skilltriage.moorai.dev/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http skilltriage-mcp https://skilltriage.moorai.dev/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "skilltriage-mcp": {
      "url": "https://skilltriage.moorai.dev/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "skilltriage-mcp": {
      "serverUrl": "https://skilltriage.moorai.dev/mcp"
    }
  }
}

Let your agent find its tools

Find servers like SkillTriage MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

See all 7,317

Do you run SkillTriage MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing

SkillTriage MCP

Endpoint and access

What you can do with it

Source and maintenance

Protocol and capabilities

Server-provided instructions

Tools

Prompts

Resources

30-day availability

Maintenance history

Connect from your client

Claude Code

Codex

Cursor

Cline

VS Code

Gemini CLI

Claude Desktop

Windsurf

Let your agent find its tools

Other developer tools servers

Do you run SkillTriage MCP?