jupyter-ai
An open source extension that connects AI agents to computational notebooks in JupyterLab.
Jupyter AI is an MCP server implementation that exposes JupyterLab computational notebooks and environments to AI agents through the Model Context Protocol. It enables agents to read and write files, execute terminal commands, and interact with Jupyter notebooks programmatically. The server integrates with frontier AI agents via the Agent Client Protocol, providing a permission-based system for controlled agent actions. Developers can extend functionality by adding custom MCP servers for domain-specific tools and resources.
Key Features
Use Cases
- 01Connect Claude, Gemini, or other AI agents to Jupyter notebooks for code generation and analysis
- 02Enable agents to execute data science workflows by running commands in JupyterLab environments
- 03Build domain-specific AI assistants with custom MCP servers for specialized research tools
- 04Collaborate with AI agents on computational experiments with file and context sharing
- 05Automate notebook tasks through agent-controlled file operations and terminal commands
- 06Create reproducible research workflows where agents interact with computational environments
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
jupyter-ai — FAQ
What is the Jupyter AI MCP server?+
Jupyter AI includes a built-in MCP server that allows AI agents to interact with JupyterLab environments, including reading and writing files, executing terminal commands, and working with computational notebooks. It connects agents to your Jupyter environment through the Model Context Protocol.
How do I install Jupyter AI?+
Install Jupyter AI using pip with 'pip install jupyter-ai', then install the agent of your choice (such as Claude or Gemini). Agents are automatically detected when their dependencies are present. Full setup instructions are available in the Getting Started documentation.
Which AI agents work with Jupyter AI?+
Jupyter AI supports frontier AI agents including Claude, GitHub Copilot, Gemini, Mistral, and others that implement the Agent Client Protocol (ACP). Any ACP-compatible agent can connect to the Jupyter MCP server.
Do I need API keys to use Jupyter AI?+
Yes, you will need API keys or credentials for the specific AI agents you want to use (such as Anthropic API key for Claude or Google API key for Gemini). The Jupyter AI extension itself is open source and free to use.
Is Jupyter AI free and open source?+
Yes, Jupyter AI is an open source extension under the JupyterLab organization and is free to use. However, the AI agents you connect to may have their own pricing and API costs.
Can I add custom MCP servers to Jupyter AI?+
Yes, Jupyter AI is designed to be extensible and allows you to add custom MCP servers to provide agents with domain-specific tools, resources, and prompts. Developers can also build custom agent personas using the entry points API.
How do I install jupyter-ai?+
Open the source repository on GitHub and follow its README. jupyter-ai is a mcp server — MCP Agents Market links you directly to the official repo.
Is jupyter-ai free?+
jupyter-ai is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.