Better Native Jupyter Notebook MCP Server

A VS Code / Cursor extension that exposes Jupyter notebook manipulation via MCP (Model Context Protocol): read/edit/run cells and capture outputs. Works with Claude Code, Cursor Agent, Windsurf, and any MCP-compatible AI assistant.

Install: VS Code Marketplace · Open VSX · GitHub

[!IMPORTANT] This project is still pre-alpha so it's very rough on the edge. Working in multiple windows is unstable.

Why connect to VS Code Runtime API?

There are currently two main architectures to give AI agents access to Jupyter notebooks. This project was heavily inspired by both - kudos to these teams for pioneering the space:

Architecture 1: File-based (e.g., cursor-notebook-mcp)

These servers read/write .ipynb files directly using libraries like nbformat.

Pros: No server dependencies, works out-of-the-box

Cons:

• Cannot execute code - agents can only edit cells, user must run them manually
• UI sync issues - VS Code may show stale content until you revert/reopen
• The .ipynb JSON format is verbose (~3x more tokens than raw code)
• Race conditions if you edit while agent writes

Architecture 2: Jupyter Server API (e.g., jupyter-mcp-server)

These servers connect to Jupyter's REST API and can execute code through the kernel.

Pros: Can execute code, best choice for standalone remote JupyterLab/JupyterHub deployments

Cons:

• Requires running JupyterLab separately (jupyter lab --port 8888)
• Auth setup: tokens, URLs, environment variables
• You end up running two UIs: one for notebook and another for AI
• If you open the notebook in VS Code you create another source of truth (Jupyter server state vs your editor)

Architecture 3: VS Code / Cursor Runtime API (this extension)

We're introducing a third architecture - hooking directly into Cursor/VS Code's Notebook API, the same API the editor uses internally.

Pros:

• Zero config - just install, server starts automatically
• Faster reads (direct memory access, no serialization)
• Executes code in your existing kernel (the one VS Code already manages)
• Changes appear instantly in the editor with full undo/redo support
• Single source of truth: what you see is what the agent sees
• Works with remote kernels - if VS Code connects to a remote Jupyter server, so does the agent

Cons:

• Only works inside VS Code / Cursor (won't help if you use JupyterLab web UI)

When to use what

Features

• Execute code in the active kernel and retrieve outputs
• Full cell manipulation - insert, edit, delete, move cells
• Read cell contents and outputs including images (base64)
• Search and navigate - find text, get notebook outline
• Bulk operations - add multiple cells, clear all outputs

Tools (15)

Navigation & Reading

Cell Manipulation

Execution & Outputs

To execute ad-hoc code, use notebook_insert_cell with execute: true. To execute an existing cell, use notebook_run_cell.

Any open notebook can be targeted with notebook_uri, on screen or not. A run in a notebook on screen happens in the cell, with its output under it. A run in a notebook that is not on screen goes to that notebook's kernel: the output comes back to the agent but is not shown under the cell, and your view never moves. notebook_show brings a notebook into view first; the notebook-mcp.showNotebookToRun setting does that automatically for every run.

{
  "content": "print('hello')",
  "type": "code",
  "index": 0,
  "language": "python",
  "execute": false
}

{
  "index": 0,
  "content": "# New content"
}

{
  "query": "import pandas",
  "case_sensitive": false,
  "context_lines": 1
}

{
  "from_index": 5,
  "to_index": 0
}

{
  "cells": [
    {"content": "# Header", "type": "markdown"},
    {"content": "x = 1", "type": "code", "language": "python"}
  ],
  "index": 0
}

{
  "index": 0
}

Setup

This fork is installed from its own build, never the Marketplace (its extension ID, Submersible.better-notebook-mcp-server, is not published, so VS Code never auto-updates it):

npm ci --ignore-scripts
npm run package
code --install-extension better-notebook-mcp-server-*.vsix

On first start the extension writes a random token to ~/.config/notebook-mcp/token (mode 0600). Every request must send it as Authorization: Bearer <token>; requests carrying an Origin header (any browser page) or a non-loopback Host (DNS rebinding) are refused. Register it with Claude Code so the token is read from that file on each connect, never copied into config:

claude mcp add-json --scope user notebook \
  '{"type":"http","url":"http://127.0.0.1:49777/mcp","headersHelper":"printf %s \"{\\\"Authorization\\\":\\\"Bearer $(tr -d \"\\n\" < \"$HOME/.config/notebook-mcp/token\")\\\"}\""}'

[!ATTENTION] The server starts automatically when VS Code / Cursor opens. Look for the 🪐 :49777 indicator in the status bar.

Configuration

Performance

Tested with a 471-cell notebook (~2.8MB, 1MB outputs):

[!NOTE] Read operations are sub-millisecond because they access in-memory data structures directly. Write operations (~7ms) go through VS Code's edit pipeline for undo/redo support.

Requirements

• VS Code 1.85+ or Cursor 0.43+
• Jupyter extension

Architecture

┌─────────────────────────────────────────────────────────────────────────┐
│                         VS Code / Cursor                                │
│                                                                         │
│  ┌───────────────────────────────────────────────────────────────────┐  │
│  │                    Jupyter Extension                              │  │
│  │                                                                   │  │
│  │   Notebook Document  ◄───►  Kernel (Python)  ───►  Outputs        │  │
│  │                                    ▲                              │  │
│  └────────────────────────────────────┼──────────────────────────────┘  │
│                                       │                                 │
│  ┌────────────────────────────────────┼──────────────────────────────┐  │
│  │              Notebook MCP Server Extension                        │  │
│  │                                    │                              │  │
│  │   ┌────────────────────────────────┴───────────────────────────┐  │  │
│  │   │                  HTTP Server (:49777)                      │  │  │
│  │   │                                                            │  │  │
│  │   │  execute_code  insert_cell  list_cells  get_output  ...    │  │  │
│  │   └────────────────────────────────────────────────────────────┘  │  │
│  └───────────────────────────────────────────────────────────────────┘  │
└─────────────────────────────────────────────────────────────────────────┘
                                    │
                                    │ HTTP (MCP Protocol)
                                    ▼
                    ┌───────────────────────────────┐
                    │           AI Agent            │
                    │   (Claude Code, Cursor, etc)  │
                    └───────────────────────────────┘

How It Works

1. Extension embeds an HTTP-based MCP server (port 49777)
2. AI agent (Claude Code, Cursor Agent, etc.) sends tool calls via MCP protocol
3. Server uses VS Code / Cursor APIs to manipulate the active notebook
4. Changes appear instantly in the editor
5. Outputs are captured and returned to the agent

This enables true interactive notebook sessions with AI agents in VS Code and Cursor.