Docker Code Runner MCP server

The MCP Code Runner is a server that allows you to execute code in isolated container or virtual machine environments. It integrates with the Model Context Protocol (MCP) to provide secure code execution capabilities for AI applications or development workflows.

Installation

Prerequisites

• Python installed on your system
• Access to command line/terminal
• UV package manager

Basic Setup

1. Install the MCP code runner using UV:

uv install mcp-code-runner

2. Create a configuration file named mcp-config.json in your project directory:

{
  "mcpServers": {
    "HhRwXh-Ka1FQjOFHoDM5E": {
      "name": "mcp-code-runner",
      "type": "stdio",
      "isActive": true,
      "registryUrl": "",
      "longRunning": true,
      "tags": [],
      "command": "uv",
      "args": [
        "--directory",
        "<path>",
        "run",
        "main.py",
        "--name=<container>"
      ]
    }
  }
}

3. Replace <path> with the directory path where your code will be executed, and <container> with your preferred container name.

Usage

Running Code

To execute code in a container environment:

uv --directory /path/to/code run main.py --name=my-container

Configuration Options

The configuration file supports several important options:

• name: Identifier for the MCP server
• type: Communication protocol (stdio is standard)
• isActive: Whether the server is enabled
• longRunning: Set to true for persistent container sessions
• command: The command to execute
• args: Command line arguments

Advanced Usage

For more complex scenarios, you can customize the arguments:

"args": [
  "--directory",
  "/home/user/projects/code",
  "run",
  "main.py",
  "--name=python-container",
  "--memory=2g",
  "--timeout=60"
]

Troubleshooting

Common Issues

• If the container fails to start, check that the path specified exists
• Ensure UV is properly installed and accessible in your PATH
• Verify your configuration file syntax is valid JSON

Logs

To view execution logs for debugging:

uv logs --name=<container>

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "mcp-code-runner" '{"name":"mcp-code-runner","type":"stdio","isActive":true,"registryUrl":"","longRunning":true,"tags":[],"command":"uv","args":["--directory","<path>","run","main.py","--name=<container>"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "mcp-code-runner": {
            "name": "mcp-code-runner",
            "type": "stdio",
            "isActive": true,
            "registryUrl": "",
            "longRunning": true,
            "tags": [],
            "command": "uv",
            "args": [
                "--directory",
                "<path>",
                "run",
                "main.py",
                "--name=<container>"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "mcp-code-runner": {
            "name": "mcp-code-runner",
            "type": "stdio",
            "isActive": true,
            "registryUrl": "",
            "longRunning": true,
            "tags": [],
            "command": "uv",
            "args": [
                "--directory",
                "<path>",
                "run",
                "main.py",
                "--name=<container>"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect