mcpsec

An AI-driven dynamic protocol fuzzer for the Model Context Protocol (MCP). Prove runtime exploitability by discovering state violations, transport crashes, and application-layer logic flaws (SSRF, LFI) before your AI agents do.

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

claude mcp add mcpsec uvx mcpsec

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