Mcpcheck

io.github.joeyoughPublished by GitHub account joeyoughv1.0.1Updated Oct 24, 2026

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

VerifiedStreamable HTTPWeb executableDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

Scans MCP servers for tool-poisoning, security, auth and license issues before install and returns a trust score.

What you can do
Check an MCP server's trust: get a 0-100 trust score and A-F grade from a registry name, GitHub repo or remote MCP URL. Live-connect to remote servers and analyze their exposed tools for tool-poisoning, with a capability inventory. Scan TLS, auth, license and repository trust signals. Run the same scan engine as the trust check for a pre-install inspection.
When to use it
Use it before installing an MCP server to get a risk read, such as checking a remote server's exposed tools for tool-poisoning or comparing trust scores across a registry name, GitHub repo and remote URL.
Requirements
Remote endpoint; no packages, environment variables or headers needed. Network access to the endpoint, and to the target server when scanning a remote one.
Before you install
Scanning a remote server live-connects to that third-party endpoint and analyzes its tools, so the target URL and related details go to this service. The trust score is advisory and does not replace your own review.

Installation

In SourceWeft

  1. Open Mcpcheck in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.joeyough%2Fmcpcheck/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "mcpcheck": {
      "type": "http",
      "url": "https://mcpcheck.netlify.app/mcp"
    }
  }
}

README

This repository has no README.

Tools

2

check_mcp_trust

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.

Parameterstargetrequired

scan_mcp_server

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.

Parameterstargetrequired

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.