MCPgee
MCPgee
MCPgeeMCPgee

Jupyter

v1.0.0•Data Science & ML•stable

MCP server for Jupyter Notebooks and JupyterLab

jupytermcpai-integration
Share:
31
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Jupyter?

Jupyter is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for jupyter notebooks and jupyterlab

MCP server for Jupyter Notebooks and JupyterLab

This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP server for Jupyter Notebooks and JupyterLab

Use Cases

Execute code and manage Jupyter Notebook and JupyterLab environments.
Integrate AI-assisted data analysis with Jupyter environments.
ihrpr

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedFeb 17, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

NPM

npx -y jupyter_mcp_server

Manual Installation

npx -y jupyter_mcp_server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Jupyter

Jupyter MCP Server connects AI assistants to live Jupyter Notebook and JupyterLab environments, enabling Claude to read, write, and execute notebook cells in real time. It exposes six tools for reading notebooks with or without outputs, accessing individual cell results, adding new code or markdown cells, editing existing cells by ID, and executing cells to capture their output. This makes it possible to drive data science and machine learning workflows entirely through natural language — asking Claude to run analyses, fix errors, and iterate on code within a running Jupyter session.

Prerequisites

  • Python 3.10 or higher installed
  • uv package manager installed (recommended)
  • JupyterLab installed and running in a virtual environment
  • An MCP-compatible client such as Claude Desktop
  • The UV_PROJECT_ENVIRONMENT variable pointing to your Jupyter venv path
1

Create a virtual environment and install JupyterLab

Set up a dedicated virtual environment for Jupyter and install JupyterLab into it. This venv path will be needed for the MCP server configuration.

uv venv --seed
source .venv/bin/activate
uv pip install jupyterlab
2

Start JupyterLab

Launch JupyterLab from the virtual environment. Keep it running while using the MCP server.

.venv/bin/jupyter lab
3

Note your venv path

The MCP server needs the absolute path to the Jupyter virtual environment. Note down the full path to the .venv directory.

echo $(pwd)/.venv
4

Configure Claude Desktop with the MCP server

Add the Jupyter MCP server to your claude_desktop_config.json, pointing UV_PROJECT_ENVIRONMENT to your Jupyter venv path.

5

Restart Claude Desktop and test

Restart Claude Desktop and ask it to read a notebook file. Always use the full absolute path to notebook files — relative paths are not supported.

Jupyter Examples

Client configuration

Add this to your claude_desktop_config.json. Replace the UV_PROJECT_ENVIRONMENT path with the absolute path to your Jupyter virtual environment.

{
  "mcpServers": {
    "jupyter-notebook-manager": {
      "command": "uv",
      "args": ["run", "--with", "mcp-server-jupyter", "mcp-server-jupyter"],
      "env": {
        "UV_PROJECT_ENVIRONMENT": "/absolute/path/to/.venv"
      }
    }
  }
}

Prompts to try

Use these prompts to interact with Jupyter notebooks through Claude. Always provide full absolute paths to notebook files.

- "Read the notebook at /Users/me/notebooks/analysis.ipynb and summarize what it does"
- "Add a new code cell to /Users/me/notebooks/analysis.ipynb with a matplotlib bar chart"
- "Execute cell 3 in the notebook at /Users/me/notebooks/analysis.ipynb and show me the output"
- "Edit the code in cell 2 of analysis.ipynb to fix the KeyError on the 'sales' column"
- "Read just the source code of /Users/me/notebooks/model.ipynb without the cell outputs"

Troubleshooting Jupyter

Server fails with 'UV_PROJECT_ENVIRONMENT is not set' or kernel connection error

Set UV_PROJECT_ENVIRONMENT to the absolute path of the .venv directory where JupyterLab is installed. Run 'which jupyter' inside the venv to confirm the correct path.

Cell execution returns empty output or no results

Ensure JupyterLab is running and connected to a kernel before asking Claude to execute cells. The MCP server requires an active JupyterLab session — it does not start Jupyter automatically.

Notebook edits made by Claude are not visible in JupyterLab

After the MCP server modifies a notebook, manually reload it in JupyterLab (File > Reload Notebook from Disk). Automatic reload on external changes is not yet supported.

Frequently Asked Questions about Jupyter

What is Jupyter?

Jupyter is a Model Context Protocol (MCP) server that mcp server for jupyter notebooks and jupyterlab It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Jupyter?

Install via npm with the command: npx -y jupyter_mcp_server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Jupyter?

Jupyter works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Jupyter free to use?

Yes, Jupyter is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Jupyter Alternatives — Similar Data Science & ML Servers

Looking for alternatives to Jupyter? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.

Ultrarag

★ 5.6k

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

RocketRide

★ 3.1k

📇 🏠 - MCP server that exposes RocketRide AI pipelines as t

Aix Db

★ 2.1k

Aix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。

NeMo Data Designer

★ 1.9k

🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

PaperBanana

★ 1.7k

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

MiniMax

★ 1.5k

Bridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.

Browse More Data Science & ML MCP Servers

Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Data Science & MLBrowse All Servers

Quick Config Preview

{ "mcpServers": { "jupyter": { "command": "npx", "args": ["-y", "jupyter_mcp_server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Jupyter?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides