Playwright-based testing and eval framework for MCP servers with LLM-as-a-judge
Latest release v1.1.1 — Release 1.1.1 · 10 Jul 2026
3 files for Codex, OpenCode and Claude Code: mcp-server-tester AGENTS.md, mcp-server-tester CLAUDE.md, mcp-server-tester — 7,253 tokens loaded in every session.
AGENTS.md A 7,248 tok CLAUDE.md A 5 tok .claude/settings.json A — These files are gleanwork/mcp-server-tester'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.