mcpscan

obielin/mcpscan

★ 0 stars Python 🤖 AI/LLM Updated 4d ago

Security scanner for MCP (Model Context Protocol) servers. Detects prompt injection, unsafe auth, path traversal and over-broad permissions. Zero dependencies.

View on GitHub →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mcpscan": {
      "command": "uvx",
      "args": [
        "mcpscan"
      ]
    }
  }
}

Or install with pip: pip install mcpscan

README Excerpt

**Security scanner for MCP (Model Context Protocol) servers. Detects prompt injection in tool descriptions, unsafe authentication, path traversal, and over-broad permissions. Zero dependencies.** --- MCP (Model Context Protocol) is now the standard for connecting AI agents to tools. Anthropic, OpenAI, Google, and Microsoft all support it. There are 16,000+ public MCP servers.

Tools (3)

mcpscanobielinpypi

Topics

agentic-aiai-securityanthropicclaudedeveloper-toolsllmmcpmodel-context-protocolowaspprompt-injectionred-teamscannersecuritytool-poisoning

mcpscan

Quick Install

README Excerpt

Tools (3)

Topics

Related AI/LLM Servers