Author verifiable eval records through a draft → review → revise → submit loop with server-enforced graders; compile to JSONL/CSV/Inspect/lm-eval via MCP. STDIO or Streamable HTTP.
Latest release v0.1.6 — v0.1.6: Draft validation and numeric grading · 13 Oct 2026
2 files for Codex, OpenCode and Claude Code: evals-mcp-server AGENTS.md, evals-mcp-server CLAUDE.md — 15,604 tokens loaded in every session.
AGENTS.md A 7,802 tok CLAUDE.md A 7,802 tok These files are cyanheads/evals-mcp-server's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.