datalayer/jupyter-mcp-server
🪐 🔧 Model Context Protocol (MCP) Server for Jupyter.
This project helps AI agents connect to and control Jupyter Notebooks in real-time. It takes instructions from an AI client (like Claude Desktop) and translates them into actions within a Jupyter environment, such as running code, managing cells, and reading outputs. It's designed for developers building AI agents or applications that need to automate data analysis, scientific computing, or scripting workflows within Jupyter.
937 stars. Used by 2 other packages. Actively maintained with 16 commits in the last 30 days. Available on PyPI.
Use this if you are developing an AI agent and need it to programmatically interact with Jupyter Notebooks, execute code, manage cells, and receive real-time updates.
Not ideal if you are an end-user looking for a direct interface to run Jupyter Notebooks without involving an AI agent.
Stars
937
Forks
147
Language
Python
License
BSD-3-Clause
Category
Last pushed
Mar 01, 2026
Commits (30d)
16
Dependencies
13
Reverse dependents
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/datalayer/jupyter-mcp-server"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related servers
PrefectHQ/fastmcp
🚀 The fast, Pythonic way to build MCP servers and clients.
samuelgursky/davinci-resolve-mcp
MCP server integration for DaVinci Resolve
tadata-org/fastapi_mcp
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
alondmnt/joplin-mcp
MCP server for the Joplin note taking app
czasg/pywss
一个轻量级的 Python Web 框架，一站式集成 MCP SSE、StreamHTTP 和 MCPO 协议，助你轻松构建MCP Server🔥