MCP Code Executor

The MCP Code Executor is an MCP server designed to enable Large Language Models (LLMs) to execute Python code within a designated Conda environment. This setup grants LLMs access to specific libraries and dependencies defined within that environment.

<a href="https://glama.ai/mcp/servers/45ix8xode3"><img width="380" height="200" src="https://glama.ai/mcp/servers/45ix8xode3/badge" alt="Code Executor MCP server" /></a>

Features

• Executes Python code generated from LLM prompts.
• Runs code within a specified Conda environment.
• Offers a configurable code storage directory.

Prerequisites

• Node.js
• Conda
• A created Conda environment

Configuration

Configure the server by adding a configuration block to your MCP servers configuration file, specifying the command to execute the server (node), arguments including the path to the built index.js file, and environment variables for the code storage directory (CODE_STORAGE_DIR) and Conda environment name (CONDA_ENV_NAME).

Usage

Once configured, LLMs can execute Python code by generating a file in the specified CODE_STORAGE_DIR, which is then run within the designated Conda environment. LLMs reference this MCP server in their prompts to trigger code generation and execution.

Contributing

Contributions are welcome through issues and pull requests.

License

This project is licensed under the MIT License.