Datalayer Jupyter MCP Server

🚀 Jupyter MCP Server

This is a server that combines JupyterLab with Claude Desktop, enabling real - time collaboration in notebooks and providing useful tools.

🚀 Quick Start

Launch JupyterLab

Make sure the following components are installed. Modifications to notebooks can be viewed via Jupyter Real - Time Collaboration (RTC).

pip install jupyterlab jupyter-collaboration ipykernel

Then, start JupyterLab using the following command:

jupyter lab --port 8888 --IdentityProvider.token MY_TOKEN --ip 0.0.0.0 

⚠️ Important Note

Set --ip to 0.0.0.0 so that the MCP server running in the Docker container can access your local JupyterLab.

💻 Usage Examples

Use with Claude Desktop

To use it with Claude Desktop, add the following content to claude_desktop_config.json:

⚠️ Important Note

Ensure that the ports of SERVER_URL and TOKEN match those used in the jupyter lab command. NOTEBOOK_PATH should be relative to the JupyterLab startup directory.

MacOS and Windows

{
  "mcpServers": {
    "jupyter": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "SERVER_URL",
        "-e",
        "TOKEN",
        "-e",
        "NOTEBOOK_PATH",
        "datalayer/jupyter-mcp-server:latest"
      ],
      "env": {
        "SERVER_URL": "http://host.docker.internal:8888",
        "TOKEN": "MY_TOKEN",
        "NOTEBOOK_PATH": "notebook.ipynb"
      }
    }
  }
}

Linux

{
  "mcpServers": {
    "jupyter": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "SERVER_URL",
        "-e",
        "TOKEN",
        "-e",
        "NOTEBOOK_PATH",
        "--network=host",
        "datalayer/jupyter-mcp-server:latest"
      ],
      "env": {
        "SERVER_URL": "http://localhost:8888",
        "TOKEN": "MY_TOKEN",
        "NOTEBOOK_PATH": "notebook.ipynb"
      }
    }
  }
}

✨ Features

Tools

The current server provides two tools:

1. add_execute_code_cell

• Add and execute a code cell in a Jupyter notebook.
• Input:
  • cell_content (string): The code to be executed.
• Return: A success message.

2. add_markdown_cell

• Add a Markdown cell in a Jupyter notebook.
• Input:
  • cell_content (string): The Markdown content.
• Return: A success message.

📦 Installation

Build

docker build -t datalayer/jupyter-mcp-server .

Install via Smithery

To automatically install the Jupyter MCP Server for Claude Desktop via Smithery:

npx -y @smithery/cli install @datalayer/jupyter-mcp-server --client claude