AgentsID MCP Scanner

Name: AgentsID MCP Scanner
Author: stevenkozeniesky02

@stevenkozeniesky02

リポジトリ

基本情報

カテゴリ

開発者ツール

トランスポート

stdio

作者

stevenkozeniesky02

投稿者

stevenkozeniesky02

AgentsID MCP Scanner について

Security scanner for MCP servers. Scores any server against the AgentsID trust framework live scan via npx or lookup pre-scanned results from the public registry of 15,983 servers. Returns trust score (0–100), grade (A–F), and findings across injection, permissions, validation, a

#mcp #security #scanner#agentsid#ai-agents

AgentsID MCP Scanner の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "agentsid-scanner": {
      "command": "npx",
      "args": [
        "@agentsid/mcp-scanner"
      ]
    }
  }
}

AgentsID MCP Scanner のツール

Runs a security scan on a specific MCP server and returns its trust score (0–100), letter grade (A–F), and list of security findings. Provide an npx command (e.g. 'npx @modelcontextprotocol/server-github') or an HTTP URL. The scan checks only the named server's tool descriptions and input schemas. Returns JSON with score, grade, and findings.

Looks up a pre-scanned MCP server's trust score, grade, and findings from the AgentsID registry. Returns cached results for the specific named package without spawning any process. Use this to check a known package before installing it.

Checks the session posture for a specific MCP server from its registry report. Returns whether the specific server exposes session-related tools, what external services it connects to, and whether its profile indicates it handles sensitive user data. Useful for evaluating a specific server before connecting an agent to it.

概要

What is AgentsID MCP Scanner?

AgentsID MCP Scanner is a security analysis tool for MCP servers. It evaluates servers against the AgentsID trust framework, returning a trust score (0–100), grade (A–F), and detailed findings across injection, permissions, validation, and auth categories. It is intended for developers and users who need to assess the security posture of MCP servers.

How

「開発者ツール」の他のコンテンツ

BetterBugs

The BetterBugs MCP (Model Context Protocol) enables you to load BetterBugs bug reports (via report links) directly to your preferred AI Agents and developer environments with MCP Client capabilities (such as Cursor, VS C

NextBlock CMS

NextBlock

Open-source Next.js + Supabase CMS with a per-site MCP server: scaffold a site, then create pages, posts, navigation, media and SEO from Claude, Cursor or any MCP client. Streamable HTTP with a bearer token you mint in y

SSH MCP Server

hypnosis

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.