trw-mcp

MCP server for AI coding agents — persistent engineering memory, knowledge compounding, and spec-driven development workflows. Part of TRW Framework.

[](https://python.org) [](https://trwframework.com/license) [](https://modelcontextprotocol.io/) [](https://trwframework.com/docs)

> Every AI coding tool resets to zero. TRW is the one that doesn't.

trw-mcp is the MCP server component of TRW (The Real Work) — a methodology layer for AI-assisted development that turns each coding session's discoveries into permanent institutional knowledge. It works alongside trw-memory, the standalone memory engine.

• trw-mcp (this repo): MCP server with 24 tools, 24 skills, 18 agents
• [trw-memory](https://github.com/wallter/trw-memory): Standalone memory engine with hybrid retrieval, scoring, and lifecycle

trw-mcp is a Model Context Protocol server that gives AI coding agents persistent engineering memory. It records what you learn during development sessions — patterns, gotchas, architecture decisions — and recalls relevant knowledge at the start of every new session. Over time, your AI coding assistant accumulates project-specific expertise instead of starting from scratch every time.

The server also manages structured run tracking (phases, checkpoints, events), build verification (pytest + mypy), spec-driven development with AARE-F PRDs, and CLAUDE.md auto-generation from high-impact learnings.

[Knowledge compounding](https://trwframework.com/docs) in practice: 225 PRDs, 64+ sprint