patchwork — Codebase Conventions for AI Agents MCP Server
io.github.SaiNarayana-B/patchwork
What this kind of tool is for
- Automate a build, test, or deployment step you repeat by hand.
- Review or refactor code in an existing repository without leaving your agent.
- Bridge an internal service or CLI into the agent toolset.
How to compare servers like this
- Scope of control:
- Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
- Environment fit:
- Match the runtime it expects (Node, Python, a container) to what you actually run.
- Maintenance signal:
- Check the last-commit date — dev tooling that lags upstream breaks first.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the patchwork — Codebase Conventions for AI Agents MCP server?
Scan any codebase, generate CONVENTIONS.md, expose conventions as MCP tools for AI agents.
How to install patchwork — Codebase Conventions for AI Agents
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"patchwork": {
"command": "uvx",
"args": [
"patchwork-conventions"
]
}
}
}Related MCP servers

Frappe Dev MCP Server
MCP server for Frappe/ERPNext development with AI assistance for DocTypes, bench commands, and APIs

Agentic SDLC MCP
Agentic SDLC governance and security controls for AI coding agents working with GitHub.

AEC Model Bridge
AI-orchestrated integration for Revit, Rhino, Navisworks, and Power BI through a single MCP hub.

AI-powered bridge connecting Revit, Rhino, Navisworks, and Power BI through a single MCP interface.

Doodleworks MCP
Hand-drawn explainer illustrations in your AI host, via an MCP App with an interactive viewer.
