Jupyter MCP Server

<!-- ~ Copyright (c) 2023-2024 Datalayer, Inc. ~ ~ BSD 3-Clause License --> [](https://datalayer.io) [](https://github.com/sponsors/datalayer) <div align="center"> <!-- omit in toc --> # 🪐✨ Jupyter MCP Server **An [MCP](https://modelcontextprotocol.io) server developed for AI to connect and manage Jupyter Notebooks in real-time** *Developed by [Datalayer](https://github.com/datalayer)* [](https://pypi.org/project/jupyter-mcp-server) [](https://pepy.tech/project/jupyter-mcp-server) [](https://hub.docker.com/r/datalayer/jupyter-mcp-server) [](https://opensource.org/licenses/BSD-3-Clause) <table> <tr> <td width="60%"> 📢 **Upcoming JupyterCon 2025**: We'll be presenting Jupyter MCP Server at [JupyterCon 2025](https://jupytercon2025.sched.com/event/28H3z) on November 4! Join us to learn about ✨ AI-powered notebook interactions and the future of 🪐 Jupyter workflows. </td> <td width="40%" align="center"> [](https://jupytercon2025.sched.com/event/28H3z) </td> </tr> </table>  > 🚨 **Latest Release: v17.0**: **JupyterLab Mode Integration!** Enhanced UI integration with automatic notebook opening. [📋 Read more in the release notes](https://jupyter-mcp-server.datalayer.tech/releases) </div> ## 📖 Table of Contents - [Key Features](#-key-features) - [Tools Overview](#-tools-overview) - [Getting Started](#-getting-started) - [Best Practices](#-best-practices) - [Contributing](#-contributing) - [Resources](#-resources) ## 🚀 Key Features - ⚡ **Real-time control:** Instantly view notebook changes as they happen. - 🔁 **Smart execution:** Automatically adjusts when a cell run fails thanks to cell output feedback. - 🧠 **Context-aware:** Understands the entire notebook context for more relevant interactions. - 📊 **Multimodal support:** Support different output types, including images, plots, and text. - 📚 **Multi-notebook support:** Seamlessly switch between multiple notebooks. - 🎨 **JupyterLab integration:** Enhanced UI integration like automatic notebook opening. - 🤝 **MCP-compatible:** Works with any MCP client, such as Claude Desktop, Cursor, Windsurf, and more. Compatible with any Jupyter deployment (local, JupyterHub, ...) and with [Datalayer](https://datalayer.ai/) hosted Notebooks. ## 🔧 Tools Overview The server provides a rich set of tools for interacting with Jupyter notebooks, categorized as follows: ### Server Management Tools | Name | Description | | :--------------- | :----------------------------------------------------------------------------------------- | | `list_files` | List files and directories in the Jupyter server's file system. | | `list_kernels` | List all available and running kernel sessions on the Jupyter server. | ### Multi-Notebook Management Tools | Name | Description | | :----------------- | :--------------------------------------------------------------------------------------- | | `use_notebook` | Connect to a notebook file, create a new one, or switch between notebooks. | | `list_notebooks` | List all notebooks available on the Jupyter server and their status | | `restart_notebook` | Restart the kernel for a specific managed notebook. | | `unuse_notebook` | Disconnect from a specific notebook and release its resources. | | `read_notebook` | Read notebook cells source content with brief or detailed format options. | ### Cell Operations and Execution Tools | Name | Description | | :------------------------- | :------------------------------------------------------------------------------- | | `read_cell` | Read the full content (Metadata, Source and Outputs) of a single cell. | | `insert_cell` | Insert a new code or markdown cell at a specified position. | | `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, supports multimodal output including images. | | `insert_execute_code_cell` | Insert a new code cell and execute it in one step. | | `execute_code` | Execute code directly in the kernel, supports magic commands and shell commands. | ### JupyterLab Integration *Available only when JupyterLab mode is enabled. It is enabled by default.* | Name | Description | | :----------------------- | :--------------------------------------------------------------------------------- | | `notebook_run-all-cells` | Execute all cells in the current notebook sequentially | For more details on each tool, their parameters, and return values, please refer to the [official Tools documentation](https://jupyter-mcp-server.datalayer.tech/tools). ## 🏁 Getting Started For comprehensive setup instructions—including `Streamable HTTP` transport, running as a Jupyter Server extension and advanced configuration—check out [our documentation](https://jupyter-mcp-server.datalayer.tech/). Or, get started quickly with `JupyterLab` and `STDIO` transport here below. ### 1. Set Up Your Environment ```bash 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 ``` ### 2. Start JupyterLab ```bash # Start JupyterLab on port 8888, allowing access from any IP and setting a token jupyter lab --port 8888 --IdentityProvider.token MY_TOKEN --ip 0.0.0.0 ``` > [!NOTE] > If you are running notebooks through JupyterHub instead of JupyterLab as above, you should: > > - Set the environment variable `JUPYTERHUB_ALLOW_TOKEN_IN_URL=1` in the single-user environment. > - Ensure your API token (`MY_TOKEN`) is created with `access:servers` scope in the Hub. ### 3. Configure Your Preferred MCP Client Next, configure your MCP client to connect to the server. We offer two primary methods—choose the one that best fits your needs: - **📦 Using `uvx` (Recommended for Quick Start):** A lightweight and fast method using `uv`. Ideal for local development and first-time users. - **🐳 Using `Docker` (Recommended for Production):** A containerized approach that ensures a consistent and isolated environment, perfect for production or complex setups. <details> <summary><b>📦 Using uvx (Quick Start)</b></summary> First, install `uv`: ```bash pip install uv uv --version # should be 0.6.14 or higher ``` See more details on [uv installation](https://docs.astral.sh/uv/getting-started/installation/). Then, configure your client: ```json { "mcpServers": { "jupyter": { "command": "uvx", "args": ["jupyter-mcp-server@latest"], "env": { "JUPYTER_URL": "http://localhost:8888", "JUPYTER_TOKEN": "MY_TOKEN", "ALLOW_IMG_OUTPUT": "true" } } } } ``` </details> <details> <summary><b>🐳 Using Docker (Production)</b></summary> **On macOS and Windows:** ```json { "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" } } } } ``` **On Linux:** ```json { "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" } } } } ``` </details> > [!TIP] > > 1. **Port Configuration**: Ensure the `port` in your Jupyter URLs matches the one used in the `jupyter lab` command. For simplified config, set this in `JUPYTER_URL`. > 1. **Server Separation**: Use `JUPYTER_URL` when both services are on the same server, or set individual variables for advanced deployments. The different URL variables exist because some deployments separate notebook storage (`DOCUMENT_URL`) from kernel execution (`RUNTIME_URL`). > 1. **Authentication**: In most cases, document and runtime services use the same authentication token. Use `JUPYTER_TOKEN` for simplified config or set `DOCUMENT_TOKEN` and `RUNTIME_TOKEN` individually for different credentials. > 1. **Notebook Path**: The `DOCUMENT_ID` parameter specifies the path to the notebook the MCP client default to connect. It should be relative to the directory where JupyterLab was started. If you omit `DOCUMENT_ID`, the MCP client can automatically list all available notebooks on the Jupyter server, allowing you to select one interactively via your prompts. > 1. **Image Output**: Set `ALLOW_IMG_OUTPUT` to `false` if your LLM does not support mutimodel understanding. For detailed instructions on configuring various MCP clients—including [Claude Desktop](https://jupyter-mcp-server.datalayer.tech/clients/claude_desktop), [VS Code](https://jupyter-mcp-server.datalayer.tech/clients/vscode), [Cursor](https://jupyter-mcp-server.datalayer.tech/clients/cursor), [Cline](https://jupyter-mcp-server.datalayer.tech/clients/cline), and [Windsurf](https://jupyter-mcp-server.datalayer.tech/clients/windsurf) — see the [Clients documentation](https://jupyter-mcp-server.datalayer.tech/clients). ## ✅ Best Practices - Interact with LLMs that supports multimodal input (like Gemini 2.5 Pro) to fully utilize advanced multimodal understanding capabilities. - Use a MCP client that supports returning image data and can parse it (like Cursor, Gemini CLI, etc.), as some clients may not support this feature. - Break down complex task (like the whole data science workflow) into multiple sub-tasks (like data cleaning, feature engineering, model training, model evaluation, etc.) and execute them step-by-step. - Provide clearly structured prompts and rules (👉 Visit our [Prompt Templates](prompt/README.md) to get started) - Provide as much context as possible (like already installed packages, field explanations for existing datasets, current working directory, detailed task requirements, etc.). ## 🤝 Contributing We welcome contributions of all kinds! Here are some examples: - 🐛 Bug fixes - 📝 Improvements to existing features - ✨ New feature development - 📚 Documentation improvements and prompt templates For detailed instructions on how to get started with development and submit your contributions, please see our [**Contributing Guide**](CONTRIBUTING.md). ### Our Contributors [](https://github.com/datalayer/jupyter-mcp-server/graphs/contributors) ## 📚 Resources Looking for blog posts, videos, or other materials about Jupyter MCP Server? 👉 Visit the [**Resources section**](https://jupyter-mcp-server.datalayer.tech/resources) in our documentation for more! [](https://star-history.com/#datalayer/jupyter-mcp-server&type=Date) ______________________________________________________________________ <div align="center"> **If this project is helpful to you, please give us a ⭐️** Made with ❤️ by [Datalayer](https://github.com/datalayer) </div>