🪐✨ Jupyter MCP Server

What is 🪐✨ Jupyter MCP Server?

An open-source MCP server that enables AI agents to connect to and manage Jupyter Notebooks in real-time. It bridges AI assistants with Jupyter environments, allowing direct notebook creation, cell execution, and output retrieval. Developed by Datalayer.

How to use 🪐✨ Jupyter MCP Server?

Install via pip install jupyter-mcp-server and configure your MCP client with environment variables JUPYTER_URL, JUPYTER_TOKEN, and ALLOW_IMG_OUTPUT. Run using uvx for quick start or Docker for production. Alternatively, run as a Jupyter Server extension. The server supports STDIO and Streamable HTTP transports.

Key features of 🪐✨ Jupyter MCP Server

• Real-time notebook control with instant output viewing.
• Smart execution that adjusts after cell failures.
• Context-aware understanding of entire notebooks.
• Multimodal output support (images, plots, text).
• Multi-notebook switching and management.
• JupyterLab integration with additional commands.

Use cases of 🪐✨ Jupyter MCP Server

• AI-assisted code development and debugging in Jupyter.
• Automated data analysis and visualization workflows.
• Interactive exploration of notebooks via natural language.
• Orchestrating multi-notebook experiments with an AI agent.
• Real-time collaborative editing with JupyterLab integration.

FAQ from 🪐✨ Jupyter MCP Server

What MCP clients are supported?

Works with any MCP client, including Claude Desktop, Cursor, Windsurf, and others.

How do I configure the server?

Set JUPYTER_URL, JUPYTER_TOKEN, and ALLOW_IMG_OUTPUT environment variables. A MCP_TOKEN is also required since version 1.0.0.

Is Docker supported?

Yes. Use the datalayer/jupyter-mcp-server Docker image with environment variables passed at runtime.

What are the runtime requirements?

Python environment with JupyterLab 4.4.1+, jupyter-collaboration, jupyter-mcp-tools, ipykernel, and pycrdt. Starting v1.0.2, datalayer_pycrdt is no longer needed.

Does it support JupyterHub or Google Colab?

Support for JupyterHub and Google Colab deployments is actively being developed; user feedback is welcome.