Robust new jupyter server

Name: Robust new jupyter server
Author: kshitijdesai99

@kshitijdesai99

代码仓库

关于 Robust new jupyter server

I was facing issues with https://github.com/datalayer/jupyter-mcp-server

#jupyter #jupyter-lab #jupyter-server #python

基本信息

分类

数据与分析

传输方式

stdio

发布者

kshitijdesai99

提交者

kshitij desai

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "jupyter_mcp_server_kshitij": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "jupyterlab",
        "jupyter-collaboration",
        "ipykernel",
        "pycrdt"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Robust new jupyter server?

This server provides a Docker-based client that connects to a Jupyter server using multi-collaborative protocol support, enabling MCP clients (such as Claude Desktop) to execute code in a Jupyter notebook.

How to use Robust new jupyter server?

Set up a Python 3.12.10 environment, install dependencies (jupyterlab, jupyter-collaboration, etc.), start a Jupyter server with a token, build the Docker image named notebook-client, and add the appropriate configuration to your Claude Desktop config.json. Key commands include jupyter lab --port 8888 --IdentityProvider.token MY_TOKEN --ip 0.0.0.0 and docker build -t notebook-client ..

Key features of Robust new jupyter server

Docker-based client for easy deployment
Supports multi-collaborative Jupyter notebooks
Integrates with Claude Desktop via MCP
Token-based authentication with Jupyter server
Uses jupyter-collaboration and pycrdt for real-time sync

Use cases of Robust new jupyter server

Running Jupyter notebook code from Claude Desktop
Collaborative notebook execution with multiple MCP clients
Isolated code execution in a Docker container
Automating Jupyter workflows via MCP

FAQ from Robust new jupyter server

What dependencies are required?

Python 3.12.10, Docker, Git, and packages including jupyterlab, jupyter-collaboration, ipykernel, pycrdt, jupyter_server_ydoc, and the two client libraries.

How does authentication work?

The server uses a token set via --IdentityProvider.token MY_TOKEN. The same token must be passed as the TOKEN environment variable in the Docker client configuration.

What should I do if I get a WebSocketClosedError?

Delete the existing notebook.ipynb, create a new notebook from the Jupyter UI, and rename it to notebook.ipynb. This issue is known to occur on macOS.

How is the client configured for Claude Desktop?

Add an entry to config.json with command "docker" and arguments that run the container with environment variables for notebook path, server URL, and token.

Where does the notebook data live?

The notebook file (notebook.ipynb) resides on the host machine, and the client container reads/updates it over HTTP from the running Jupyter server.