EV
@modelcontextprotocol
Reference / test server with prompts, resources, and tools.
87k1w ago0 toolslocal
$
npx -y @modelcontextprotocol/server-everythingModel Context Protocol (MCP) Server for Jupyter.
$ pip install jupyterlab==4.4.1 jupyter-collaboration==4.0.2 jupyter-mcp-tools>=0.1.4 ipykernel pycrdtOr add it with the Claude CLI: claude mcp add datalayer-jupyter-mcp-server
list_fileslist_kernelsconnect_to_jupyteruse_notebooklist_notebooksrestart_notebookunuse_notebookread_notebookread_cellinsert_celldelete_cellmove_celloverwrite_cell_sourceedit_cell_sourceexecute_cellinsert_execute_code_cellexecute_code{ "mcpServers": { "datalayer-jupyter-mcp-server": { "command": "pip", "args": ["install", "jupyterlab==4.4.1", "jupyter-collaboration==4.0.2", "jupyter-mcp-tools>=0.1.4", "ipykernel", "pycrdt"], "env": { "MCP_TOKEN": "<your-mcp-token>", "MY_TOKEN": "<your-my-token>", "JUPYTER_TOKEN": "<your-jupyter-token>", "JUPYTER_URL": "<your-jupyter-url>", "DOCUMENT_TOKEN": "<your-document-token>", "RUNTIME_TOKEN": "<your-runtime-token>" } } } }
Paste under mcpServers in your config, then restart Claude Desktop. For Claude Code, reference this server in your project's CLAUDE.md.
Reference / test server with prompts, resources, and tools.
npx -y @modelcontextprotocol/server-everythingOfficial GitHub server for integration with repository management, PRs, issues, and more.
A high-level framework for building MCP servers in Python