Submit Log in

Jupyter MCP Server

by Datalayer

v1.3.4

BSD-3-Clause

Repository Docs

Featured Developer Tools

jupyternotebookspythondata-sciencesandbox

Summary

Drive live Jupyter notebooks from an agent — read and edit cells, execute code, see rich outputs, and run against local JupyterLab or a cloud sandbox.

Features

Read, insert, edit and execute cells in a live notebook
Multimodal outputs — return plots and images back to the agent
Manage multiple notebooks in a single session
Code-sandbox variants for Datalayer, Kaggle, Google Colab and Modal
STDIO, Streamable HTTP and Jupyter Server extension transports
Claude Code plugin and a hosted deployment option

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

Open your agent's MCP configuration file.
Merge the snippet below into it, filling in the environment variables with your own values.
Restart the agent — the "Jupyter MCP Server" tools will be available.

{
  "mcpServers": {
    "jupyter-mcp-server": {
      "command": "uvx",
      "args": [
        "jupyter-mcp-server@latest"
      ],
      "env": {
        "JUPYTER_URL": "http://localhost:8888",
        "JUPYTER_TOKEN": "<YOUR_TOKEN>",
        "ALLOW_IMG_OUTPUT": "true"
      }
    }
  }
}

Claude Code

Add the server with a single CLI command.

claude mcp add jupyter-mcp-server -e JUPYTER_URL=http://localhost:8888 -e JUPYTER_TOKEN=<YOUR_TOKEN> -e ALLOW_IMG_OUTPUT=true -- uvx jupyter-mcp-server@latest

Claude Desktop

Add the server to claude_desktop_config.json (Settings → Developer → Edit Config).

{
  "mcpServers": {
    "jupyter-mcp-server": {
      "command": "uvx",
      "args": [
        "jupyter-mcp-server@latest"
      ],
      "env": {
        "JUPYTER_URL": "http://localhost:8888",
        "JUPYTER_TOKEN": "<YOUR_TOKEN>",
        "ALLOW_IMG_OUTPUT": "true"
      }
    }
  }
}

Cursor

{
  "command": "uvx",
  "args": [
    "jupyter-mcp-server@latest"
  ],
  "env": {
    "JUPYTER_URL": "http://localhost:8888",
    "JUPYTER_TOKEN": "<YOUR_TOKEN>"
  }
}

Docker (macOS and Windows). On Linux use --network=host and a localhost JUPYTER_URL.

{
  "command": "docker",
  "args": [
    "run",
    "-i",
    "--rm",
    "-e",
    "JUPYTER_URL",
    "-e",
    "JUPYTER_TOKEN",
    "datalayer/jupyter-mcp-server:latest"
  ],
  "env": {
    "JUPYTER_URL": "http://host.docker.internal:8888",
    "JUPYTER_TOKEN": "<YOUR_TOKEN>"
  }
}

Description

Datalayer's Jupyter MCP Server connects an agent to a running Jupyter kernel rather than to notebook files on disk. That distinction is the whole point: the agent can insert and edit cells, execute them, read the outputs — including images, when ALLOW_IMG_OUTPUT is enabled — and iterate the way a person would, with state carried between cells instead of re-running a script from scratch each time.

It handles multiple notebooks in one session, exposes server and sandbox management tools alongside cell operations, and ships MCP prompts as well as tools. A JupyterLab integration adds further tools that can be switched on at the command line.

Where the kernel lives is configurable. Beyond a local JupyterLab, sandbox variants run the code on Datalayer, Kaggle (batch or interactive, with optional GPU), Google Colab or Modal, so the same agent workflow scales from a laptop to accelerated cloud compute. A hosted version of the server is also available, and there is a Claude Code plugin (/plugin marketplace add datalayer/jupyter-mcp-server).

Setup is a short list: pip install jupyterlab jupyter-collaboration jupyter-mcp-tools ipykernel, start JupyterLab with a token, then point the client at it. Distributed under the BSD 3-Clause licence.

Related MCP Servers

MCP: deja-vu

by Vladislav Shulcz

New

Indexes the coding-agent sessions already sitting on your disk — months of history from before you installed it — and serves them back over MCP. 3.5 GB searched in ~1.5 ms, no LLM, no embeddings.

Developer ToolsDatabases & Data

MCP: Azure DevOps MCP Server

by Microsoft

New

Microsoft's official MCP server for Azure DevOps - work items, repos, pipelines, wikis, test plans and iterations, reachable from any MCP client in plain language.

Developer Tools