Python Notebook MCP Server

<h1>Python Notebook MCP</h1> MCP server enabling AI assistants to interact with Jupyter notebooks through the Model Context Protocol.

Local serverstdioPython

What is the Python Notebook MCP MCP server?

Connect Python Notebook MCP to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Python Notebook MCP MCP server enabling AI assistants to interact with Jupyter notebooks through the Model Context Protocol. The python notebook mcp mcp server is what makes that connection.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • initialize_workspaceREQUIRED FIRST STEP. Sets the absolute path for the workspace
  • list_notebooks — Lists all .ipynb files found within the workspace directory
  • create_notebook — Creates a new, empty Jupyter notebook if it doesn't exist
  • read_notebook — Reads the entire structure and content of a notebook
  • read_cell — Reads the content and metadata of a specific cell by index
  • edit_cell — Modifies the source content of an existing cell by index
  • add_cell — Adds a new code or markdown cell at a specific index or the end
  • read_notebook_outputs — Reads all outputs from all code cells in a notebook
  • read_cell_output — Reads the output(s) of a specific code cell by index

Installation

Installation goes through your MCP client rather than a global install: point it at fastmcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Where it fits

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Python Notebook MCP's toolset — initialize_workspace, list_notebooks, create_notebook and 6 more — is a fair guide to whether it matches your workflow. It is maintained by UsamaK98; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Python Notebook MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Python Notebook MCP.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
initialize_workspace**REQUIRED FIRST STEP.** Sets the absolute path for the workspace.
list_notebooksLists all .ipynb files found within the workspace directory.
create_notebookCreates a new, empty Jupyter notebook if it doesn't exist.
read_notebookReads the entire structure and content of a notebook.
read_cellReads the content and metadata of a specific cell by index.
edit_cellModifies the source content of an existing cell by index.
add_cellAdds a new code or markdown cell at a specific index or the end.
read_notebook_outputsReads all outputs from all code cells in a notebook.
read_cell_outputReads the output(s) of a specific code cell by index.

How to install the Python Notebook MCP MCP server

{
  "mcpServers": {
    "python-notebook": {
      "command": "uvx",
      "args": ["fastmcp"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Python Notebook MCP to initialize workspace.
  • Use Python Notebook MCP to list notebooks.
  • Use Python Notebook MCP to create notebook.

Frequently asked questions

It connects Python Notebook MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 9 tools (initialize_workspace, list_notebooks, create_notebook, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Python Notebook MCP directly.