jupyter-mcp-server
Jupyter MCP server for real-time AI connection and management of Jupyter notebooks.
- Type
- MCP
- Transport
- http
- Open source
- Yes
- GitHub Stars
- ★ 1.2k
- Source
- mcp-github
- Repository
- github.com/datalayer/jupyter-mcp-server
Overview
The Jupyter MCP server is a service based on the Model Context Protocol (MCP) designed to enable AI to connect to, manage, and operate Jupyter notebooks in real time. It supports multiple output types (such as images, charts, and text) and intelligently handles cell execution failures. This capability allows AI to better understand the full context of a notebook and engage in more relevant interactions. Ideal for scenarios requiring automated management and operation of Jupyter notebooks.
Capabilities
- ▪Real-time viewing of notebook changes
- ▪Intelligent handling of cell execution failures
- ▪Understanding the entire notebook context
- ▪Support for multiple output types
- ▪Seamless switching between multiple notebooks
- ▪Enhanced integration with JupyterLab
Use cases
Setup
pip install jupyter-mcp-server
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How to configure MCP_TOKEN?
Configure MCP_TOKEN in the MCP client settings. See the official documentation for details.
Is JupyterHub and Google Colab supported?
Support is actively being developed—feedback is welcome.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
antivibe
Transform AI-generated code into deep learning materials to help developers understand the code.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.