MCP Code Executor

🚀 MCP Code Executor

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

🚀 Quick Start

The MCP Code Executor is designed to provide a seamless experience for LLMs to execute Python code in a controlled environment. After proper configuration, it can handle code generation and execution tasks efficiently.

✨ Features

• Allows the execution of Python code from LLM prompts.
• Runs code within a specified Conda environment.
• Configurable code storage directory.

📦 Installation

Prerequisites

• Node.js installed.
• Conda installed.
• The required Conda environment created.

Steps

1. Clone this repository:

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

2. Navigate to the project directory:

cd mcp_code_executor

3. Install Node.js dependencies:

npm install

4. Build the project:

npm run build

🔧 Configuration

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

{
  "mcpServers": {
    "mcp-code-executor": {
      "command": "node",
      "args": [
        "/path/to/mcp_code_executor/build/index.js" 
      ],
      "env": {
        "CODE_STORAGE_DIR": "/path/to/code/storage",
        "CONDA_ENV_NAME": "your-conda-env"
      }
    }
  }
}

Replace the placeholders:

• Replace /path/to/mcp_code_executor with the absolute path where you cloned the repository.
• Replace /path/to/code/storage with the directory where you want to store the code.
• Replace your-conda-env with the name of the Conda environment in which you want to run the code.

💻 Usage Examples

Basic Usage

After configuration, the MCP Code Executor will allow the LLM to generate files in the specified CODE_STORAGE_DIR and run code in the Conda environment defined by CONDA_ENV_NAME.

The LLM can generate and execute code by referencing this MCP server in the prompt.

# Assume the LLM generates the following Python code
print("Hello, MCP Code Executor!")