MCP servers
agent-eval
Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
Remotes
This server publishes no hosted endpoint. Run one of its packages locally.
Packages
agent-regress-cli · pypi 0.1.8 · stdio
claude mcp add --transport stdio agent-eval -- uvx agent-regress-cli==0.1.8Server details
- Registry name
- io.github.RudrenduPaul/agent-eval
- Version
- 0.1.8
