MCP servers
LLM Eval Harness
Run a golden set and gate LLM model swaps on accuracy, with latency and cost per request.
Remotes
This server publishes no hosted endpoint. Run one of its packages locally.
Packages
ghcr.io/razilzul/llm-eval-harness:1.0.0 · oci · stdio
claude mcp add --transport stdio llm-eval-harness -- docker run -i --rm ghcr.io/razilzul/llm-eval-harness:1.0.0Server details
- Registry name
- io.github.razilzul/llm-eval-harness
