KodHau MCP
The Governance Layer for your AI Agents
KodHau MCP is a Model Context Protocol server that injects a team's tribal knowledge—PR history, architecture decisions, rejected approaches, and code review comments—into AI coding agents before they write any code. It runs locally so code and PR data never leave the user's machine, and integrates with tools like Cursor and Claude Code. The product helps AI agents understand not just what code exists, but why decisions were made.
KodHau scans closed PRs for architecture decisions and review comments, then exposes a single MCP tool that injects relevant tribal knowledge into the AI agent's context before it modifies any file or function.
Software developers and engineering teams using AI coding agents
Background.
- Status
- launched
- Business model
- freemium
- Company
- KodHau
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.