jupyter-mcp-server

Level ARemote

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

Overview

Jupyter MCP Server, built by Datalayer, is an MCP server that lets AI agents connect to and manage Jupyter Notebooks in real time, reading and writing notebooks and executing code. It works with local Jupyter and JupyterHub, and can scale code sandboxes from local to cloud environments such as Datalayer, Kaggle, Google Colab, Modal, and E2B. It offers OAuth 2.1 sign-in with scoped permissions and is free and open source.

⭐ 1.3kDevelopment ToolsPythonRepo ↗Updated 2026-11-20

Installation

MCP client config (paste into mcp.json)

{
  "mcpServers": {
    "datalayer-jupyter-mcp-server": {
      "url": "https://mcp.datalayer.run/mcp"
    }
  }
}

Agent install prompt

Copy and paste into Cursor / Claude / other agents to install this MCP for you

Please read this MCP repository and install it into my current environment:
https://github.com/datalayer/jupyter-mcp-server

Known working client config (can write into mcp.json):
{
  "mcpServers": {
    "datalayer-jupyter-mcp-server": {
      "url": "https://mcp.datalayer.run/mcp"
    }
  }
}

Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.

Related servers