sage-book-server 0.1.2

Sage Book Server Package

Jupyter MCP Server

A basic description of your Jupyter MCP Server package.

Installation

pip install sage-book-server

Or using uv:

uv pip install sage-book-server

Running the Server

1. Start Jupyter Lab:

jupyter lab --port 8888 --IdentityProvider.token MY_TOKEN --ip 0.0.0.0

2. In a separate terminal, start the MCP server:

sage-book-server

3. Add the following variables to your environment

# Claude Configuration
CLAUDE_API_KEY=""
CLAUDE_MODEL_ID="claude-3-7-sonnet-20250219"
CLAUDE_MODEL_URL="https://sage.alpinex.ai:8760" # use passthrough

# Gemini Configuration
GEMINI_API_KEY=""
GEMINI_MODEL_ID="gemini-2.5-pro-preview-03-25"
GEMINI_MODEL_URL="https://generativelanguage.googleapis.com"

# Server Configuration
MCP_SERVER_URL="http://localhost:8888"
MCP_SERVER_PORT="7888"

# override by docker
JUPYTER_SECRET_KEY="MY_TOKEN"
DATABASE_URL=""
NOTEBOOK_DIR="./"

Notes

• Replace MY_TOKEN with your desired authentication token
• The server will be accessible at http://localhost:8888
• Make sure to keep all three processes running (Jupyter Lab and both MCP server/client instances)

MCP Server Setup with uv

1. Install uv (if not already installed)

   curl -Ls https://astral.sh/uv/install.sh | bash
   

2. Navigate to your directory

   cd /path/to/your/project
   

3. Create a uv-managed virtual environment (Python 3.10)

   uv venv --python=3.10 .venv
   

4. Activate the environment

   source .venv/bin/activate
   

5. Install all required packages

   uv pip install -r requirements.txt
   

6. Run the MCP server

   uv run sage-book-server