← All projects

KodHau MCP

The Governance Layer for your AI Agents

Dev Toolsmcpai-agentscode-reviewpr-historycursorclaude-codetribal-knowledge
KodHau MCP screenshot

About

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.

Problem

AI coding agents lack the institutional knowledge and historical context that senior engineers carry, leading to incorrect or dangerous code suggestions.

For

Software developers and engineering teams using AI coding agents

How it works

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.

Business model

freemium

Status

launched

Company

KodHau

Similar projects