mcp-test-bench

Level FSource

Open-source evaluation framework for MCP servers powered by Claude. Auto-discovers tools, generates test scenarios, runs LLM-as-judge scoring to assess correctness and safety, audits for security issues, and visualizes traces in a web dashboard.

⭐ 0DevOps & DeploymentTypeScriptRepo ↗Updated 2026-07-23

Installation

View source repo →

Related servers