🪐✨ Jupyter MCP Server

🪐 ✨ Model Context Protocol (MCP) Server for Jupyter.

Catalog onlyCatalog onlySTDIO

Overview

Jupyter MCP Server is an implementation of the Model Context Protocol (MCP) that facilitates interaction with Jupyter notebooks running in a local JupyterLab environment.

To use the Jupyter MCP Server, first install JupyterLab and its dependencies, then start JupyterLab with specific commands. You can also configure it to work with Claude Desktop by modifying the configuration file.

Integration with Jupyter notebooks for real-time collaboration. - Ability to add and execute code cells and markdown cells in notebooks. - Support for Docker to run the server in a containerized environment.

Collaborative coding and data analysis in Jupyter notebooks.
Automating the execution of code cells in educational settings.
Enhancing productivity in data science projects by integrating with other tools.

Add to your AI client

Use these steps to connect 🪐✨ Jupyter MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "jupyter-mcp-server-datalayer": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-jupyter-mcp-server-datalayer"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "jupyter-mcp-server-datalayer": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-jupyter-mcp-server-datalayer"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "jupyter-mcp-server-datalayer": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-jupyter-mcp-server-datalayer"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "jupyter-mcp-server-datalayer": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-jupyter-mcp-server-datalayer"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "jupyter-mcp-server-datalayer": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-jupyter-mcp-server-datalayer"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "jupyter-mcp-server-datalayer": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-jupyter-mcp-server-datalayer"
      ]
    }
  }
}

FAQ

What is the Model Context Protocol?

The Model Context Protocol is a standard for managing and sharing context in machine learning models and applications.

Can I run Jupyter MCP Server on any operating system?

Yes, Jupyter MCP Server can be run on MacOS, Windows, and Linux with appropriate configurations.

Is there a way to install Jupyter MCP Server automatically?

Yes, you can install it automatically via Smithery.

Developer tools