mcp-notebooks
About
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…
Details
- Author
- Neuron1c
- Downloads
- 156
- Categories
- Other
Jump to
- 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.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
mcp-notebooksCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
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.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp-notebooks": {
"mcp-notebooks": {
"command": "docker",
"args": [
"build",
".",
"-t",
"mcp-notebooks:latest"
]
}
}
}
}McpServers
{
"mcp-notebooks": {
"command": "docker",
"args": [
"build",
".",
"-t",
"mcp-notebooks:latest"
]
}
}mcp-notebooks
Notebook execution MCP serverPretty dangerous to use in its current state
Rationale
Why not just execute code with literally any other already existing python execution server. This MCP server allows your LLM to progressively execute code and react to mistakes faster in a sort of EDA fashion. Variables are retained in the kernel and can be used in future executions.
Claude install
Okay listen buddy, it's not a one line process and run some node something. This really really should be run in a docker environment to protect your system from the AI overlor... I mean Claude. So go install docker and come back
Welcome back. This is not on DockerHub yet so run the following commands:
git clone git@github.com:Neuron1c/mcp-notebooks.git
cd mcp-notebooks
docker build . -t mcp-notebooks:latest
Halfway there, add the following to your claude_desktop_config.json
StdIO
{
"mcpServers": {
"notebooks": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"mcp-notebooks:latest"
]
}
}
}
SSE
Or run it manually
docker run -p 3001:3001 mcp-notebooks:latest
And now the config.json
{
"mcpServers": {
"notebooks": {
"command": "npx",
"args": [
"supergateway",
"--sse",
"http://localhost:3001/sse"
]
}
}
}
Add Python Libraries
As it stands the project dependencies are scoped to the bare minimum of what's needed to run the server. To add more you need to install poetry, after you have fought with that (protip use pipx)
uv add your-package
recommended packages to add
- numpy
- pandas
- scikit-learn
- matplotlib
- seaborn
I've found the AI really tries to use the graphing packages when demonstrating things to your
TODO
- View notebooks - Sandbox the environment more - Scheme a data ingestion scenario (Kedro catalog?) - Dependency injection (Or just let the user pull and build their own container)Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
