Notebook Intelligence
A JupyterLab extension supporting Claude Code, Copilot, Ollama, and OpenAI-compatible LLMs, with MCP, skills, plugins, and notebook agents.
What is Notebook Intelligence?
Notebook Intelligence is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to jupyterlab extension supporting claude code, copilot, ollama, and openai-compatible llms, with mcp, skills, plugins, and notebook agents.
A JupyterLab extension supporting Claude Code, Copilot, Ollama, and OpenAI-compatible LLMs, with MCP, skills, plugins, and notebook agents.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A JupyterLab extension supporting Claude Code, Copilot, Olla
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx notebook-intelligenceConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Notebook Intelligence
Notebook Intelligence is a JupyterLab extension that integrates multiple AI providers — including Claude Code, GitHub Copilot, OpenAI-compatible endpoints, and Ollama — directly into your notebook workflow. It exposes an MCP server interface so external tools can interact with notebooks, and it supports MCP client connections to bring external tools into JupyterLab itself. Data scientists and researchers use it to get inline code suggestions, chat-based notebook editing, cell-output explanations, and agent-driven notebook execution without leaving JupyterLab.
Prerequisites
- Python 3.9 or higher with pip installed
- JupyterLab 4.x installed in your environment
- At least one supported AI provider credential: ANTHROPIC_API_KEY for Claude, an OpenAI-compatible API key, or a running Ollama instance
- An MCP client if using the bundled MCP server feature (Claude Desktop or Claude Code CLI)
Install the Notebook Intelligence extension
Install the package with pip. JupyterLab will auto-detect and enable the extension.
pip install notebook-intelligenceLaunch JupyterLab
Start JupyterLab normally. The Notebook Intelligence icon will appear in the left sidebar.
jupyter labConfigure your AI provider
Click the NBI icon in the sidebar, then open Settings (gear icon). Choose your provider (Anthropic Claude, Copilot, OpenAI-compatible, or Ollama) and enter your credentials.
Set environment variables for automated or CI setups
Use environment variables to pre-configure the provider without the UI. ANTHROPIC_API_KEY supplies Claude credentials; NBI_CHAT_MODEL_PROVIDER pins the provider; NBI_CHAT_MODEL_ID pins the specific model.
export ANTHROPIC_API_KEY=sk-ant-...
export NBI_CHAT_MODEL_PROVIDER=anthropic
export NBI_CHAT_MODEL_ID=claude-3-5-sonnet-20241022Configure MCP servers for the extension (optional)
To connect external MCP tools into JupyterLab, add server entries to ~/.jupyter/nbi/mcp.json. This allows the Notebook Intelligence agent to use tools from other MCP servers.
Use inline suggestions and chat
In any notebook cell, press Ctrl+G (or Cmd+G on macOS) for inline code generation. Open the chat panel to ask questions, run notebook agents, or explain cell errors.
Notebook Intelligence Examples
Client configuration
MCP server config for Claude Desktop to expose Notebook Intelligence as an MCP server that can control JupyterLab.
{
"mcpServers": {
"notebook-intelligence": {
"command": "python",
"args": ["-m", "notebook_intelligence.mcp_server"],
"env": {
"ANTHROPIC_API_KEY": "sk-ant-...",
"NBI_CHAT_MODEL_PROVIDER": "anthropic"
}
}
}
}Prompts to try
Interact with JupyterLab notebooks through the chat panel or via an MCP client.
- "Generate a pandas data cleaning function that drops duplicates and fills NaN values."
- "Explain the error in the cell output above and suggest a fix."
- "Create a new notebook cell that plots a histogram of the 'age' column using matplotlib."
- "Run all cells in the current notebook and summarize the outputs."
- "What Ollama models do I have available for local inference?"Troubleshooting Notebook Intelligence
Notebook Intelligence icon does not appear in JupyterLab sidebar after install
Run `jupyter labextension list` to confirm the extension is enabled. If not listed, rebuild JupyterLab with `jupyter lab build`. Ensure JupyterLab 4.x is installed.
Claude provider shows authentication error
Verify ANTHROPIC_API_KEY is set correctly and is a valid key starting with 'sk-ant-'. You can also enter it directly in the NBI Settings panel rather than via environment variable.
MCP servers defined in mcp.json are not appearing as tools in the agent
Check the JSON syntax of ~/.jupyter/nbi/mcp.json and ensure each server entry has valid 'command' and 'args' fields. Restart JupyterLab after editing the file.
Frequently Asked Questions about Notebook Intelligence
What is Notebook Intelligence?
Notebook Intelligence is a Model Context Protocol (MCP) server that jupyterlab extension supporting claude code, copilot, ollama, and openai-compatible llms, with mcp, skills, plugins, and notebook agents. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Notebook Intelligence?
Follow the installation instructions on the Notebook Intelligence GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Notebook Intelligence?
Notebook Intelligence works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Notebook Intelligence free to use?
Yes, Notebook Intelligence is open source and available under the GPL-3.0 license. You can use it freely in both personal and commercial projects.
Notebook Intelligence Alternatives — Similar Developer Tools Servers
Looking for alternatives to Notebook Intelligence? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Notebook Intelligence in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Notebook Intelligence?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.