mcp-server-jupyter
An MCP server for managing and interacting with Jupyter notebooks programmatically.

接入你的智能体
从发布者处安装。不是 PlugMCP 端点。
远程 URL 还是本机命令? 两种安装方式的区别
来自发布者
An MCP server for managing and interacting with Jupyter notebooks programmatically.

MCP server for Jupyter Notebooks and JupyterLab
The server provides six tools for notebook manipulation:
read_notebook_with_outputs: Read a notebook's content including cell outputs
notebook_path (string)read_notebook_source_only: Read notebook content without outputs
notebook_path (string)read_output_of_cell: Read output of a specific cell
notebook_path (string)cell_id (string)add_cell: Add new cell to notebook
notebook_path (string)source (string)cell_type (string): "code" or "markdown"position (integer): insertion index (-1 to append)edit_cell: Modify existing cell content
notebook_path (string)cell_id (string): Unique ID of the cell to editsource (string)execute_cell: Execute a specific cell and return its output
notebook_path (string)cell_id (string)By using uv to run Jupyter notebooks it's much easier to manage venv and package installations.
Follow uv jupyter docummentation for more details.
uv venv --seed
source .venv/bin/activate
uv pip install jupyterlab
.venv/bin/jupyter lab
NOTE: this environment should be used as UV_PROJECT_ENVIRONMENT env variable in MCP server (next step). Run in the same folder where Jupyter started.
echo $(pwd)/.venv
PyPi package:
// ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"Jupyter-notebook-manager": {
"command": "uv",
"args": ["run", "--with", "mcp-server-jupyter", "mcp-server-jupyter"],
"env": {
"UV_PROJECT_ENVIRONMENT": "/path/to/venv_for_jupyter/.venv"
}
}
}
}
Git repo fork
// ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"Jupyter-notebook-manager": {
"command": "uv",
"args": [
"run",
"--directory",
"/Users/inna/mcp-server-jupyter/src/mcp_server_jupyter",
"mcp-server-jupyter"
],
"env": {
"UV_PROJECT_ENVIRONMENT": "/path/to/venv_for_jupyter/.venv"
}
}
}
}
Open or create a notebook in JupyterLab/Jupyter Notebook
Get the full path to your notebook:
In Claude Desktop chat:
/Users/username/projects/my_notebook.ipynbImportant Notes:
This project is licensed under the MIT License. See the LICENSE file for details.
MCP server for Jupyter Notebooks and JupyterLab
工具
暂无工具列表。远程服务器在首次健康检查后会获得工具列表。
常见问题
在本页复制适用于 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 配置。它使用发布者的安装方式,而不是 PlugMCP 代理。
此记录未列出必需的环境变量。
MCP Server Jupyter 通过 stdio 在本地运行。
上次检查时间:2026-10-27。 MCP server for Jupyter Notebooks and JupyterLab