SSyncDev

Jupyter MCP Server

A JupyterLab extension to manage MCP servers.

Remote serverstreamable-httpPython

What is the Jupyter MCP server?

A JupyterLab extension to manage MCP servers. That is what the jupyter mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

This extension provides a user interface and backend infrastructure to configure and manage MCP servers directly within JupyterLab. It allows you to define which MCP servers are available for use by other JupyterLab extensions or AI assistants.

The Model Context Protocol (MCP) is an open standard that enables AI assistants and other clients to interact with various data sources, tools, and services through a unified interface. MCP servers expose resources, tools, and prompts that AI models can query and use during conversations.

  • Configuration Management — Add, edit, remove and disable MCP server configurations through a dedicated settings panel in JupyterLab
  • Multiple Server Types — Support for both HTTP (remote endpoint) and stdio (local executable) MCP servers
  • Flexible Configuration — Configure servers via:
  • JupyterLab Settings UI (persisted in browser)
  • JSON configuration files in Jupyter config directories (~/.jupyter/mcp_servers.json)
  • adding MCP servers in the manager server side (for extensions)

Getting it running

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

What it needs from you

  • JupyterLab >= 4.0.0 - Python >= 3.10

Things to watch

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Plenty of browser automation servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. It is maintained by GitHub Actions; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

How to install the Jupyter MCP server

{
  "mcpServers": {
    "jupyter-2": {
      "command": "uvx",
      "args": ["jupyter_mcp_manager"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • JupyterLab >= 4.0.0 - Python >= 3.10

Frequently asked questions

It connects Jupyter to MCP-compatible AI assistants such as Claude and Cursor. Instead of copying data back and forth by hand, the assistant works with Jupyter directly.

Alternatives to the Jupyter MCP server

Playwright

Official

Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.

Browser AutomationTypeScript★ 21.0k

Firecrawl

Official

Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.

Search & Web ScrapingRemoteTypeScript★ 4.6k

Puppeteer

Official

The original Chromium automation reference server — simple, screenshot-driven browser control.

Browser AutomationTypeScript★ 63.0k

Chrome DevTools

Official

Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.

Browser AutomationTypeScript★ 48.4k

Browser MCP

Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.

Browser AutomationRemoteTypeScript★ 38.4k

Browserbase

Official

Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.

Browser AutomationRemoteTypeScript★ 2.9k