Mcp Eval Runner is a standardized testing harness for Model Context Protocol (MCP) servers and agent workflows. It allows users to define test cases as YAML fixtures, run regression suites from their MCP client, and receive pass/fail results with diffs, supporting both live and simulation execution modes. Aimed at MCP tool developers and integrators, it emphasizes reproducible, version-controlled testing, CI integration, and robust reporting without leaving popular developer environments.
Visit Mcp Eval Runner's official website for product details and getting started.
Comprehensive guide on how to use Mcp Eval Runner, including setup and configuration.
Community forum for reporting issues and discussing enhancements related to Mcp Eval Runner.