mcp-guard

ShovalBenjer/mcp-guard
★ 1 stars Python AI/LLM Updated today
Adversarial fuzzer for MCP servers — dynamically break Model Context Protocol endpoints. Shell injection, SSRF, overflow, type confusion, prompt injection probes. Zero-dep Python core.
View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

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

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-guard": {
      "command": "uvx",
      "args": [
        "mcp-guard"
      ]
    }
  }
}

Or install with pip: pip install mcp-guard

README Excerpt

<div align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="docs/assets/logo.svg"> <img src="docs/assets/logo.svg" alt="mcp-guard" width="120"> </picture> **Adversarial fuzzer for MCP servers. Break them before they break you.** </div> --- | | Static Governance | mcp-guard | |---|---|---|

Topics

agent-securityai-agentdevsecopsllmmcpmodel-context-protocolowasppythonsecuritysecurity-scanner