Loading...
codemcp allows Claude to directly edit code, run commands, and manage Git commits in a local repository, offering auto-accept and versioning.
Boost this tool
Subscribe to listing upgrades or segmented pushes.
codemcp allows Claude to directly edit code, run commands, and manage Git commits in a local repository, offering auto-accept and versioning.
codemcp offers convenience by allowing Claude to directly modify code, but it comes with significant risks. It is safe if the user carefully configures allowed commands and closely monitors changes. It is risky if the configuration is lax, potentially leading to unintended or malicious code execution.
Performance depends on the complexity of the codebase and the speed of the LLM. Rate limiting may be encountered with Claude Pro.
Cost is primarily associated with the Claude Pro subscription. Token usage is a factor, but the subscription model aims to minimize marginal cost concerns.
uvx --fromPYTHONPATHformatRuns a code formatter on the codebase.
Modifies code files, but typically in a non-destructive way.
testRuns tests on the codebase.
Executes code, but typically within a testing environment.
None
cloud
codemcp offers convenience by allowing Claude to directly modify code, but it comes with significant risks. It is safe if the user carefully configures allowed commands and closely monitors changes. It is risky if the configuration is lax, potentially leading to unintended or malicious code execution.
The agent operates with the permissions of the user running the server. Command execution is restricted to pre-defined commands in `codemcp.toml`.
Production Tip
Carefully define and test the commands in `codemcp.toml` to ensure they are safe and effective before deploying to a production environment.
Edit the `codemcp.toml` file in your project directory and define the commands under the `[commands]` section.
codemcp automatically commits changes to Git. Use Git commands to revert to a previous commit.
Review the changes in your IDE and correct them manually. You can also revert to a previous commit if necessary.
Yes, but the value proposition is less clear compared to Claude Code.
Logs are written to `~/.codemcp/codemcp.log`. You can configure the verbosity in `~/.codemcprc`.
The `project_prompt` is loaded when you initialize the project in chats. It can be used to provide initial instructions or context to Claude.
codemcp involves code execution on your local machine, so it's crucial to carefully configure allowed commands and monitor changes. Use with caution.