Skip to content

io.github.joeyough/mcpcheck

by joeyough · remote · no sign-in to list tools · v1.0.1 · published by GitHub user joeyough

Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.

Changes · 2

2 tools: 2 change things.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http mcpcheck https://mcpcheck.netlify.app/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

2 tools

Changes things 2Claude Code: ask
  • check_mcp_trustCheck if an MCP server is safe to install: returns a trust score (0-100, grade A-F).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Check if an MCP server is safe to install: returns a trust score (0-100, grade A-F). Accepts a registry name (io.github.x/y), a GitHub repo (owner/repo), or a remote MCP URL. For remote servers it live-connects and analyzes the actual exposed tools for tool-poisoning + capabilities, and checks the backing repo (maintenance, license, security policy, auth). Call BEFORE installing or recommending any MCP server.
  • scan_mcp_serverScan and inspect an MCP server for security issues before connecting it: live tool-poisoning analysis, exposed-tool inventory + capabilities, TLS, and repo trust signals.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Scan and inspect an MCP server for security issues before connecting it: live tool-poisoning analysis, exposed-tool inventory + capabilities, TLS, and repo trust signals. Same engine as check_mcp_trust. Accepts a registry name, GitHub repo, or remote MCP URL.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http mcpcheck https://mcpcheck.netlify.app/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__mcpcheck__check_mcp_trust",
      "mcp__mcpcheck__scan_mcp_server"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as mcpcheck. Review it before you use it.