Codemcp is a pair programming MCP server that turns Claude Desktop into an autonomous coding assistant. It enables Claude to directly edit files, implement features, fix bugs, and run tests on local codebases without copying code in and out of the chat window. Key features of codemcp: - Git-versioned edits with automatic versioning of all LLM changes, enabling fine-grained rollback of agent actions - Restricted shell execution using pre-declared commands in `codemcp.toml`, preventing unrestricted shell access - IDE-agnostic workflow that works with any editor (vim, VS Code, etc.)—make changes with Claude, review in your preferred environment - Auto-accept mode for uninterrupted agent execution with review-at-the-end workflow - Test running capabilities to verify changes - Designed for use with Claude Pro subscription with zero marginal cost per action Note: The author considers this project obsolete now that Claude Code is available with Anthropic's subscription, though it remains open source and offers unique Git-versioning features.

NOTICE: claude code is available with Anthropic's $20/mo subscription, so I consider codemcp fully obsolete. However, there are some good design ideas (especially around the Git-versioning scheme) that I eventually want to port into the current generation of agentic coding clis.

codemcp

Make Claude Desktop a pair programming assistant by installing codemcp. With it, you can directly ask Claude to implement features, fix bugs and do refactors on a codebase on your computer; Claude will directly edit files and run tests. Say goodbye to copying code in and out of Claude's chat window!

codemcp offers similar functionality to other AI coding software (Claude Code, Cursor, Cline, Aider), but it occupies a unique point in the design space:

1. It's intended to be used with Claude Pro, Anthropic's $20/mo subscription offering. I like paying for my usage with a subscription plan because it means zero marginal cost for agent actions; no more feeling bad that you wasted five bucks on a changeset that doesn't work.

Note that if you have Claude Max ($100/mo), Claude Code can also be used with subscription based pricing. The value proposition for codemcp is murkier in this case (and it is definitely inferior to Claude Code in some respects), but you can still use codemcp with Claude Max if you prefer some of the other UI decisions it makes. (Also, it's open source, so you can change it if you don't like it, unlike Claude Code!)

2. It's built around auto-accept by default. I want my agent to get as far as it can without my supervision, so I can review everything in one go at the end. There are two key things that codemcp does differently than most coding agents: we forbid unrestricted shell, instead requiring you to predeclare commands the agent can use in `codemcp.toml, and we **Git version all LLM edits**, so you can roll back agent changes on a fine-grained basis and don't have to worry about forgetting to commit changes.

3. It's IDE agnostic: you ask Claude to make changes, it makes them, and then you can use your favorite IDE setup to review the changes and make further edits. I use vim as my daily driver editor, and coding environments that require VSCode or a specific editor are a turn off for me.

IMPORTANT: For master users - Major changes for token efficiency

To improve codemcp's token efficiency, on master I am in the process of changing codemcp back into a multi-tool tool (instead of a single tool whose instructions are blatted into chat when you InitProject). This means you have to manually approve tool use. Because tool use approval is persistent across multiple chats, I think this is a reasonable tradeoff to make, but if you really don't like, file a bug at refined-claude browser extension for supporting auto-approve tool use.

Installation

I recommend this specific way of installing and using codemcp:

1. Install uv and install git, if they are not installed already.

2. Install claude-mcp on your browser. This enables you to connect to SSE MCP servers directly from the website, which means you don't need to use Claude Desktop and can easily have multiple chat windows going in parallel. We expect this extension should be soon obsoleted by the rollout of Integrations. At time of writing, however, Integrations have not yet arrived for Claude Pro subscribers.

3. Run codemcp using uvx --from git+https://github.com/ezyang/codemcp@prod codemcp serve. You can add --port 1234 if you need it to listen on a non-standard port.

Pro tip: if you like to live dangerously, you can change prod to main. If you want to pin to a specific release, replace it with 0.3.0 or similar.

Pro tip: you can run codemcp remotely! If you use Tailscale and trust all devices on your Tailnet, you can do this securely by passing --host 100.101.102.103 (replace the IP with the Tailscale IP address of your node. This IP typically lives in the 100.64.0.0/10 range.) WARNING: Anyone with access to this MCP can perform arbitrary code execution on your computer, it is EXTREMELY unlikely you want to bind to 0.0.0.0.

4. Configure claude-mcp with URL: http://127.0.0.1:8000/sse` (replace the port if needed.)

5. Unfortunately, the web UI inconsistently displays the hammer icon. However, you can verify that the MCP server is working by looking for "[MCP codemcp] SSE connection opened" in the Console, or by asking Claude what tools it has available (it should say tools from codemcp are available.)

If you prefer to use Claude Desktop or have unusual needs, check