{"server":{"$schema":"https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json","name":"io.github.razilzul/llm-eval-harness","description":"Run a golden set and gate LLM model swaps on accuracy, with latency and cost per request.","title":"LLM Eval Harness","repository":{"url":"https://github.com/razilzul/llm-eval-harness","source":"github"},"version":"1.0.0","packages":[{"registryType":"oci","identifier":"ghcr.io/razilzul/llm-eval-harness:1.0.0","transport":{"type":"stdio"},"environmentVariables":[{"description":"Only needed to evaluate anthropic:* models. Not needed for mock models.","format":"string","isSecret":true,"name":"ANTHROPIC_API_KEY"},{"description":"Only needed to evaluate gemini:* models. Not needed for mock models.","format":"string","isSecret":true,"name":"GEMINI_API_KEY"}]}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","statusChangedAt":"2026-10-18T13:22:46.283666Z","publishedAt":"2026-10-18T13:22:46.283666Z","updatedAt":"2026-10-18T13:22:46.283666Z","isLatest":true}}}