code-executor

MCP Code Executor

The MCP Code Executor is an MCP server that allows LLMs to execute Python code within a specified Conda environment. This enables LLMs to run code with access to libraries and dependencies defined in the Conda environment.

Features

Execute Python code from LLM prompts
Run code within a specified Conda environment
Configurable code storage directory

Prerequisites

Node.js installed
Conda installed
Desired Conda environment created

Setup

Clone this repository:

1git clone https://github.com/bazinga012/mcp_code_executor.git

Navigate to the project directory:

1cd mcp_code_executor

Install the Node.js dependencies:

1npm install

Build the project:

1npm run build

Configuration

To configure the MCP Code Executor server, add the following to your MCP servers configuration file:

1{
2  "mcpServers": {
3    "mcp-code-executor": {
4      "command": "node",
5      "args": [
6        "/path/to/mcp_code_executor/build/index.js" 
7      ],
8      "env": {
9        "CODE_STORAGE_DIR": "/path/to/code/storage",
10        "CONDA_ENV_NAME": "your-conda-env"
11      }
12    }
13  }
14}

Replace the placeholders:

/path/to/mcp_code_executor with the absolute path to where you cloned this repository
/path/to/code/storage with the directory where you want the generated code to be stored
your-conda-env with the name of the Conda environment you want the code to run in

Usage

Once configured, the MCP Code Executor will allow LLMs to execute Python code by generating a file in the specified CODE_STORAGE_DIR and running it within the Conda environment defined by CONDA_ENV_NAME.

LLMs can generate and execute code by referencing this MCP server in their prompts.

Contributing

Contributions are welcome! Please open an issue or submit a pull request.

License

This project is licensed under the MIT License.

Contents