mcp-gauntlet

GhalebDweikat/mcp-gauntlet
★ 0 stars Python AI/LLM Updated today
Agentic evaluation harness for MCP servers. Runs a live LLM agent against a server's tools and scores wether it can actually complete tasks.
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-gauntlet": {
      "command": "uvx",
      "args": [
        "mcp-gauntlet"
      ]
    }
  }
}

Or install with pip: pip install mcp-gauntlet

Topics

agent-evaluationai-agentsclievalsevaluationllmllm-evaluationmcpmodel-context-protocolprompt-injectionpythontool-use