Repository avatar
Security
v0.2.2
active

mcpwatch

io.github.anardimontlv/mcpwatch

Check MCP servers' security grades and tool changes before your agent connects. Read-only.

Documentation

mcpwatch

Know when the tools your AI agents trust change.

MCP servers can quietly rewrite a tool's description after you approved it (a "rug pull"), and that description is read by your agent as instructions. mcpwatch checks every server in the official MCP registry daily, fingerprints the tools of every publicly reachable remote server, grades each server, and fails your CI when something you pinned drifts.

  • Static and read-only. It never runs third-party server code and never calls a tool.
  • Private by default. Your config never leaves your machine; the CLI only downloads public index files.
  • Zero dependencies. Python 3.10+ standard library.

Live index and rug-pull radar: https://www.mcpwatch.io

Quickstart

pipx install mcpwatch-io      # or: pip install mcpwatch-io

# 1. Scan a config for risky setups (leaked secrets, unpinned packages, root filesystem access, plain HTTP, ...)
mcpwatch-scan ~/.cursor/mcp.json

# 2. In your project: pin the exact tools your servers expose today...
cd your-project
mcpwatch lock .mcp.json          # writes mcpwatch.lock: commit it

# 3. ...and fail when any of them changes
mcpwatch check .mcp.json         # exit 1 on drift, 2 if the index can't be reached

Or paste a config into the browser scanner at https://www.mcpwatch.io/scan (runs locally in your browser). Tool fingerprints exist for remote servers we can reach without credentials; package-based servers are matched by name and version, and their tools are not fingerprinted (we never run their code).

Works with Claude Desktop, Claude Code (.mcp.json), Cursor and VS Code configs.

GitHub Action

Scan on every pull request:

- uses: actions/checkout@v4
- uses: anardimontlv/mcpwatch-action@v1
  with: { config: .mcp.json, fail-on: high }

Check for drift every day (rug-pull radar for your repo):

on: { schedule: [{ cron: "0 6 * * *" }] }
jobs:
  mcp-drift:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: anardimontlv/mcpwatch-action@v1
        with: { mode: check, config: .mcp.json, lock: mcpwatch.lock }

What check treats as drift

ChangeSeverity
A pinned tool's description or input schema changedhigh
Endpoint stopped requiring credentialshigh
Server disappeared from the index, or its lookup now points elsewherehigh
Tool added or removed; grade changedmedium
Endpoint now requires credentials, or tools can no longer be verifiedmedium
Fingerprints older than --max-stale days (default 3): a server can't hide by blocking the indexermedium
Server in the config but not in the lock file (not_locked)medium
Package version changed; server newly indexed; server removed from configlow (reported, does not fail)

Scanner rules

RuleFinds
MW001Secrets in config: env, headers, args, URLs, connection strings
MW002Unpinned packages (npx pkg, uvx pkg@latest)
MW004Remote server over plain HTTP
MW005Remote server without auth
MW006Filesystem root or whole home directory granted
MW007Privileged containers, host mounts, Docker socket
MW008Inline shell launch, curl | sh
MW009Flags that disable safety controls
MW101Tool poisoning: instructions aimed at the model in a tool description
MW102Tools that execute commands or delete data
MW103Invisible Unicode in tool text

Full rule reference: docs/rules.md. Methodology: docs/how-it-works.md. MCP server for agents: docs/mcp-server.md.

Grades are automated signals, not audits. Maintainers can dispute a finding from the server's page.

Plans

The scanner, the Action and the public index are free. Paid plans add watchlist alerts (email/Slack), full change history and an org-wide view. See https://www.mcpwatch.io/pricing.

License

Apache-2.0. See LICENSE and NOTICE. The hosted index, radar and paid plans are a commercial service.

PYPI
mcpwatch-io
Install Command
pip install mcpwatch-io