The Jupyter MCP server allows AI agents to interact with Jupyter Notebooks. It provides tools to execute, manage, and monitor notebooks, including kernel management, cell execution, and output retrieval. It connects to local or remote Jupyter instances via the Jupyter Notebook API. Data scientists and ML engineers use it to automate notebook workflows, integrate notebooks into larger AI pipelines, and monitor notebook execution in real-time.
The Jupyter MCP server allows AI agents to interact with Jupyter Notebooks. It provides tools to execute, manage, and monitor notebooks, including kernel management, cell execution, and output retrieval. It connects to local or remote Jupyter instances via the Jupyter Notebook API. Data scientists and ML engineers use it to automate notebook workflows, integrate notebooks into larger AI pipelines, and monitor notebook execution in real-time.
pip install jupyter-mcp-serverAdd this configuration to your claude_desktop_config.json:
{
"mcpServers": {
"datalayer-jupyter-mcp-server-github": {
"command": "uvx",
"args": [
"pip install jupyter-mcp-server"
]
}
}
}Restart Claude Desktop, then ask:
"What tools do you have available from jupyter?"
No configuration required. This server works out of the box.
"What resources are available in jupyter?"
Claude will query available resources and return a list of what you can access.
"Show me details about [specific item] in jupyter"
Claude will fetch and display detailed information about the requested item.
"Create a new [item] in jupyter with [details]"
Claude will use the appropriate tool to create the resource and confirm success.
We build custom MCP integrations for B2B companies. From simple connections to complex multi-tool setups.