MCP.so
Sign In

Jupyter_MCP_Server

@shreyu258

About Jupyter_MCP_Server

No overview available yet

Basic information

Category

Data & Analytics

Runtime

python

Transports

stdio

Publisher

shreyu258

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "Jupyter_MCP_Server": {
      "command": "uv",
      "args": [
        "run",
        "python",
        "-m",
        "ipykernel",
        "install",
        "--name",
        "jupyter-mcp"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Jupyter_MCP_Server?

Jupyter_MCP_Server connects Jupyter Notebook to Claude AI through the Model Context Protocol (MCP), enabling AI-assisted code execution, data analysis, and visualization via two-way WebSocket communication.

How to use Jupyter_MCP_Server?

Install prerequisites (Python 3.12+, uv, Claude desktop), clone the repo, create a virtual environment with uv, install the jupyter-mcp kernel, configure Claude’s desktop config to point to the MCP server script, then start a Jupyter nbclassic server, create a notebook with the jupyter-mcp kernel, run setup_jupyter_mcp_integration() to start the WebSocket server, and launch Claude.

Key features of Jupyter_MCP_Server

  • Two-way communication between Claude AI and Jupyter Notebook.
  • Cell manipulation: insert, execute, and manage notebook cells.
  • Notebook management: save and retrieve notebook information.
  • Cell execution: run specific cells or all cells.
  • Output retrieval: get text and image output from cells.
  • Image output retrieval for visualizations.

Use cases of Jupyter_MCP_Server

  • AI-assisted code development and debugging in Jupyter.
  • Automated data analysis and visualization generation.
  • Interactive exploration of datasets with natural language commands.
  • Remote control of Jupyter notebooks via Claude’s interface.
  • Streamlined scientific computing workflows with AI guidance.

FAQ from Jupyter_MCP_Server

What are the runtime requirements?

Python 3.12 or newer, the uv package manager, and the Claude AI desktop application are required.

How does the server communicate with the notebook?

It uses a WebSocket server started inside Jupyter that bridges communication between the notebook and the MCP server.

What tools does Claude gain access to?

Claude gets tools like ping, insert_and_execute_cell, save_notebook, get_cells_info, get_notebook_info, run_cell, run_all_cells, get_cell_text_output, get_image_output, edit_cell_content, and set_slideshow_type.

Where is the data stored?

The server does not persist data externally; it operates within the Jupyter notebook’s in-memory state and files saved by the user.

What transport protocol is used?

WebSocket for internal communication; the MCP server is run as a subprocess by Claude (stdin/stdout MCP transport). No authentication is described in the README.

Comments

More Data & Analytics MCP servers