An MCP server that lets AI agents connect to and manage Jupyter notebooks in real-time.
jupyter-mcp-server is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo view datalayer/jupyter-mcp-server --webOpen the official README and confirm the supported install method.
Add the server entry to your MCP client config.
Restart your agent and verify that the server tools appear.
This tool acts as a bridge between AI assistants and Jupyter notebooks. It allows an AI to view, edit, and run code in notebooks, seeing the results instantly. You can use it with any MCP-compatible client like Claude Desktop or Cursor.
Jupyter MCP Server is a Model Context Protocol (MCP) server developed by Datalayer that enables AI agents to interact with Jupyter notebooks in real-time. It provides a rich set of tools for notebook management, including creating, opening, editing, and executing cells, as well as viewing outputs such as text, images, and plots. The server supports multi-notebook workflows, smart execution that adapts to cell failures, and context-aware interactions that understand the entire notebook state. It integrates with JupyterLab for enhanced UI features and includes observability via OpenTelemetry. Compatible with any Jupyter deployment (local, JupyterHub, Google Colab) and works with any MCP client. The project is open-source under BSD-3-Clause license and has an active community.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 75 days ago.
1141 GitHub stars indicate community interest.
37 open issues signal maintenance load.
BSD-3-Clause license detected.
Let an AI assistant debug a Jupyter notebook by running cells and analyzing errors.
Automate data analysis workflows where an AI writes and executes code in notebooks.
Enable a chatbot to create interactive reports with live code and visualizations.
Use with Claude Desktop to explore and modify notebooks conversationally.
Integrate with Cursor or Windsurf to manage notebooks from within an IDE.
The server requires an MCP token for authentication; ensure it is kept secret.
Running arbitrary code from AI agents can be a security risk; use in a sandboxed environment if needed.
Network exposure should be limited to trusted clients only.
1,141
Stars
164
Forks
37
Issues
BSD-3-Clause
License
Local codebase intelligence CLI and MCP server for AI coding agents with change-safety gates and audit evidence.
An offline MCP server that indexes your codebase for semantic search, code search, and git history retrieval.
Official MCP reference servers from Anthropic. Includes servers for filesystem, GitHub, Postgres, Slack, and more.
An MCP server that lets AI agents connect to and manage Jupyter notebooks in real-time.
Data scientists who want AI assistance in their Jupyter workflow., AI/ML engineers building agents that need to interact with computational notebooks., Developers creating MCP-based tools for scientific computing and data analysis.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
The server requires an MCP token for authentication; ensure it is kept secret. Running arbitrary code from AI agents can be a security risk; use in a sandboxed environment if needed.
Similar or complementary options to evaluate include roam-code, code-memory, MCP Server Collection.
Jun 6, 2026
3 security/trust notes recorded.
Setup difficulty is 3/5.