mcp-notebooks

What is mcp-notebooks?

mcp-notebooks is an MCP server that enables an LLM to execute code progressively in a Jupyter-like kernel, retaining variables between executions for iterative exploratory data analysis (EDA). It is intended for users comfortable with Docker and willing to accept the current safety risks.

How to use mcp-notebooks?

Build the Docker image from the repository, then add it to your claude_desktop_config.json either via StdIO (docker run) or SSE (docker run on port 3001 plus supergateway). Additional Python libraries can be installed with uv add <package> before building.

Key features of mcp-notebooks

• Progressive code execution with variable retention in the kernel.
• Supports both StdIO and SSE transport modes.
• Runs in a Docker container for isolation.
• Built‑in kernel persists state across LLM requests.

Use cases of mcp-notebooks

• Iterative data analysis where the LLM reacts to intermediate results.
• Rapid prototyping of data‑processing scripts with an AI assistant.
• Teaching or demonstrating code that depends on previous cell outputs.

FAQ from mcp-notebooks

How do I install mcp-notebooks?

Clone the repository and run docker build . -t mcp-notebooks:latest. Then configure the server in claude_desktop_config.json as shown in the README.

What runtime environment is required?

Docker is required; the server is intended to be run inside a Docker container. It is not yet published on DockerHub.

How can I add extra Python libraries?

Add libraries with uv add your-package before building the Docker image. Recommended packages include numpy, pandas, scikit‑learn, matplotlib, and seaborn.

Is mcp-notebooks safe?

The README explicitly warns that it is “pretty dangerous to use in its current state” and strongly recommends running it inside a Docker container for isolation.

What transports are supported?

The server supports both StdIO (through a direct Docker command) and SSE (via an HTTP endpoint on port 3001 using supergateway).