npx mcpbar@latest install datalayer/jupyter-mcp-server -c claude

npx mcpbar@latest edit -c claude

{
  "mcpServers": {
    "Jupyter MCP Server": {
      "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"
      }
    }
  }
}

🪐 ✨ Jupyter MCP Server

Jupyter MCP Server is a Model Context Protocol (MCP) server implementation that provides interaction with 📓 Jupyter notebooks running in any JupyterLab (works also with your 💻 local JupyterLab).

Key features include:

• ⚡ Real-time control: view the notebook change in real-time.
• 🔁 Smart execution: automatically adjusts when a cell run fails.
• 🤝 MCP-Compatible: compatible with any MCP clients like Claude Desktop, Cursor, Windsurf, and more.

To get started:

• 📘 Follow the Usage Guide to use Jupyter-MCP-server with a MCP compatible client.
• 🧰 Dive into the Tools documentation section to understand the tools powering the server.

Looking for blog posts, videos or other resources related to Jupyter MCP Server?
👉 Check out the Resources documentation section.