Jupyter Notebook MCP server for AI agents

Jupyter MCP Server enables AI systems to connect and manage Jupyter notebooks in real-time, allowing for seamless interactions with notebook cells, execution of code, and handling of various output types. This server implements the Model Context Protocol (MCP) to bridge AI models with Jupyter environments.

Getting Started

Prerequisites

Before installing Jupyter MCP Server, ensure you have the necessary dependencies:

pip install jupyterlab==4.4.1 jupyter-collaboration==4.0.2 jupyter-mcp-tools>=0.1.4 ipykernel
pip uninstall -y pycrdt datalayer_pycrdt
pip install datalayer_pycrdt==0.12.17

Starting JupyterLab

Launch JupyterLab with the following command:

jupyter lab --port 8888 --IdentityProvider.token MY_TOKEN --ip 0.0.0.0

If using JupyterHub instead, set the environment variable JUPYTERHUB_ALLOW_TOKEN_IN_URL=1 in the single-user environment and ensure your API token has access:servers scope.

Configuring an MCP Client

Choose one of the following methods to configure your MCP client:

Using uvx (Quick Start Method)

First, install uv:

pip install uv

Then configure your client with this JSON configuration:

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

Using Docker (Production Method)

For macOS and Windows:

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

For Linux:

{
  "mcpServers": {
    "jupyter": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "JUPYTER_URL",
        "-e", "JUPYTER_TOKEN",
        "-e", "ALLOW_IMG_OUTPUT",
        "--network=host",
        "datalayer/jupyter-mcp-server:latest"
      ],
      "env": {
        "JUPYTER_URL": "http://localhost:8888",
        "JUPYTER_TOKEN": "MY_TOKEN",
        "ALLOW_IMG_OUTPUT": "true"
      }
    }
  }
}

Available Tools

Jupyter MCP Server provides various tools organized into different categories:

Server Management Tools

list_files: Recursively list files and directories in the Jupyter server's file system
list_kernels: List all available and running kernel sessions
assign_kernel_to_notebook: Connect a notebook file to a specific kernel

Multi-Notebook Management

use_notebook: Connect to a notebook file, create a new one, or switch between notebooks
list_notebooks: List all notebooks available and their status
restart_notebook: Restart the kernel for a specific managed notebook
unuse_notebook: Disconnect from a specific notebook and release its resources

Cell Operations and Execution

list_cells: List basic information for all cells
read_cell: Read the full content of a single cell
read_cells: Read the full content of all cells in the notebook
insert_cell: Insert a new code or markdown cell
delete_cell: Delete a cell at a specified index
overwrite_cell_source: Overwrite the source code of an existing cell
execute_cell: Execute a cell with timeout, supporting multimodal output
insert_execute_code_cell: Insert and execute a new code cell in one step
execute_ipython: Execute IPython code directly in the kernel

JupyterLab Integration

notebook_run-all-cells: Execute all cells in the current notebook sequentially

Best Practices

Use LLMs that support multimodal input (like Gemini 2.5 Pro) to fully utilize image output capabilities
Ensure your MCP client supports returning image data and can parse it correctly
Break down complex data science workflows into multiple sub-tasks and execute them sequentially
Match the port in your Jupyter URLs with the one used in your JupyterLab command
Set ALLOW_IMG_OUTPUT to false if your LLM does not support multimodal understanding

For more detailed information about compatible MCP clients like Claude Desktop, VS Code, Cursor, and others, refer to the Clients documentation.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "jupyter" '{"command":"docker","args":["run","-i","--rm","-e","SERVER_URL","-e","TOKEN","-e","NOTEBOOK_PATH","datalayer/jupyter-mcp-server:latest"],"env":{"SERVER_URL":"http://host.docker.internal:8888","TOKEN":"MY_TOKEN","NOTEBOOK_PATH":"notebook.ipynb"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "jupyter": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "-e",
                "SERVER_URL",
                "-e",
                "TOKEN",
                "-e",
                "NOTEBOOK_PATH",
                "datalayer/jupyter-mcp-server:latest"
            ],
            "env": {
                "SERVER_URL": "http://host.docker.internal:8888",
                "TOKEN": "MY_TOKEN",
                "NOTEBOOK_PATH": "notebook.ipynb"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "jupyter": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "-e",
                "SERVER_URL",
                "-e",
                "TOKEN",
                "-e",
                "NOTEBOOK_PATH",
                "datalayer/jupyter-mcp-server:latest"
            ],
            "env": {
                "SERVER_URL": "http://host.docker.internal:8888",
                "TOKEN": "MY_TOKEN",
                "NOTEBOOK_PATH": "notebook.ipynb"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect