pyspy-mcp is a Model Context Protocol (MCP) server that brings Python performance profiling into your LLM workflow. It wraps py-spy to let AI agents record sampling profiles, dump live stack traces, and analyze flamegraphs — so you can diagnose Python CPU bottlenecks, hot frames, and slow function calls conversationally.
Latest release v0.2.1 · 12 Jul 2026
1 file for Codex and OpenCode: pyspy-mcp AGENTS.md — 1,280 tokens loaded in every session.
AGENTS.md A 1,280 tok These files are LBurny/pyspy-mcp's own configuration — they tell Codex and OpenCode 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.