mcp-server

notebook-intelligence: Supercharge JupyterLab with Multi‑LLM Agents

Empower your data notebooks with built‑in Claude, Copilot, Ollama, and OpenAI LLM support, plus MCP‑driven skills and plugins. Ideal for founders building AI‑enhanced analytics.

From the repo · “A JupyterLab extension supporting Claude Code, Copilot, Ollama, and OpenAI-compatible LLMs, with MCP, skills, plugins, and notebook agents.”

348 stars+1★ this week68 forksPythonGuide quality 9/10 · reviewed Oct 20Updated 10/6/2026100% free · open source
What it does

Notebook-intelligence provides AI-powered coding assistance within JupyterLab, supporting various large language models (LLMs) and plugins for enhanced development productivity.

When to use it
  • •When needing intelligent code completion suggestions within Jupyter notebooks
  • •For automating repetitive coding tasks with AI-powered tools
  • •To integrate LLMs like Claude Code, Copilot, or OpenAI into the JupyterLab environment
Ready-to-paste prompt
notebook-intelligence suggest --llm claude --prompt 'Write a Python function to calculate the factorial of a given number'
Heads up: Notebook-intelligence requires a compatible LLM API key, such as a Claude Code or OpenAI API key, to function properly; ensure you have the necessary API credentials configured in your settings before using the tool.
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/notebook-intelligence && curl -fsSL https://workflowstacks.com/api/skills/notebook-intelligence/claude-skill -o ~/.claude/skills/notebook-intelligence/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How notebook-intelligence: Supercharge JupyterLab with Multi‑LLM Agents works
Codeflow
Free to inspect

Notebook-intelligence: Supercharge JupyterLab with Multi‑LLM Agents is a large Python project (~58k lines across 133 code files, plus 153 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit a month ago, GPL-3.0 license, has a test suite.

Size
Large codebase
~58k lines · 133 code files · ~8 h to skim
Setup
One-command install
Installs like a normal app. Reading the code is optional.
Runs on
Python · Node.js
No API keys detected
Python 66%TypeScript 32%CSS 2%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    src/index.ts
    Where the program starts running
  4. 4
    package.json
    Dependencies and the commands it exposes
What's in each folder
src/Core code — the actual logic65 files
notebook_intelligence/Core code — the actual logic58 files
docs/Documentation9 files
style/Themes & styling17 files
ui-tests/Folder14 files
benchmarks/Evaluations & benchmarks7 files
jupyter-config/Folder1 files
schema/Data models & types1 files
READMEHas testsDocumentedCI checksGPL-3.0 licenseUpdated this month
Quick Actions
Details
Creator
plmbr
Language
Python
Category
mcp-server
Published
9/22/2024

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/notebook-intelligence.svg)](https://workflowstacks.com/skills/notebook-intelligence?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.