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.
Instructions file CodexOpenCode
AGENTS.md instructions for LBurny/pyspy-mcp, covering py-spy / pyspy-mcp workspace instructions, project overview, directory layout, build, test, and publish and rust (py-spy).