JupyterMCP MCP Server Integration

What does “JupyterMCP” MCP Server do?

JupyterMCP is a Model Context Protocol (MCP) server designed to bridge Jupyter Notebook (version 6.x only) with AI assistants such as Claude AI. Through a WebSocket-based server, JupyterMCP enables AI models to directly interact with and control Jupyter Notebooks. This allows for AI-assisted code execution, data analysis, notebook cell management, and output retrieval. By exposing Jupyter Notebook’s core functions as MCP tools and resources, the server empowers developers to automate workflows, manipulate notebook content, and streamline data science tasks, all from within their AI assistant or MCP-compatible client. JupyterMCP is ideal for anyone seeking to combine the flexibility of Jupyter Notebooks with the intelligence of LLMs, fostering a more interactive, productive development environment.

List of Prompts

No prompt templates are mentioned in the repository documentation or code.

List of Resources

No explicit MCP resources are described in the documentation or code.

List of Tools

The following tools are described in the README and present in the server:

• Cell manipulation: Allows insertion, execution, and management of notebook cells.
• Notebook management: Save notebooks and retrieve notebook information.
• Cell execution: Run specific cells or execute all cells in a notebook.
• Output retrieval: Get output content from executed cells with text limitation options.

Use Cases of this MCP Server

• AI-assisted code execution: Developers can ask their AI assistant to run code cells or entire Jupyter Notebooks directly, speeding up iteration and reducing manual effort.
• Notebook management: Easily save, rename, or retrieve notebook metadata through natural language commands given to an AI agent.
• Cell manipulation and analysis: Insert new cells, modify existing ones, or organize code/data cells as needed for experiments, all orchestrated by the LLM.
• Automated data analysis and visualization: The AI can execute analysis or visualization cells, retrieve outputs, and even insert new analysis code based on user prompts.
• Educational and onboarding workflows: Instructors or learners can interact with notebooks through conversational interfaces, asking AI to demonstrate concepts or execute code snippets.

How to set it up

Windsurf

No setup instructions for Windsurf are provided.

Claude

1. Prerequisites: Install Python 3.12+, uv package manager, and Claude AI desktop app.
2. Clone repository:

   git clone https://github.com/jjsantos01/jupyter-notebook-mcp.git
   

3. Install Jupyter kernel:

   uv run python -m ipykernel install --name jupyter-mcp
   

4. Edit Claude config: Go to Claude > Settings > Developer > Edit Config > claude_desktop_config.json and add:

   {
     "mcpServers": {
       "jupyter": {
         "command": "uv",
         "args": [
           "--directory",
           "/ABSOLUTE/PATH/TO/PARENT/REPO/FOLDER/src",
           "run",
           "jupyter_mcp_server.py"
         ]
       }
     }
   }
   

   (Replace /ABSOLUTE/PATH/TO/ with your local path.)
5. Restart Claude: Exit and reopen the Claude desktop app to activate the MCP server.
6. (Optional) Install extra Python packages as needed.

Securing API Keys

No API keys are required or mentioned in the setup.

Cursor

No setup instructions for Cursor are provided.

Cline

No setup instructions for Cline are provided.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "MCP-name": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “MCP-name” to whatever the actual name of your MCP server is (e.g., “github-mcp”, “weather-api”, etc.) and replace the URL with your own MCP server URL.

Overview

Our opinion

JupyterMCP provides a focused integration for controlling Jupyter Notebook via MCP, with solid documentation for Claude, but lacks broader platform instructions and resource/prompt standardization. The toolset is practical for notebook automation, but the absence of explicit resource/prompt support and generalization to other clients limits its overall utility. Based on the tables, we’d rate this MCP a 5/10 for functionality and documentation.

MCP Score