未认领 · 信息来自公开资料HPSILab 已审核 · 检查于 2026年11月22日链接可访问 · 检查于 2026年11月22日
安装与连接
第三方代码:运行前请先阅读。HPSILab 审核过此说明,但不运营该服务器。
按客户端安装
claude mcp add jupyter-mcp-server -- uvx jupyter-mcp-server
有些服务器还需要额外参数或环境变量(密钥、路径等),请查看下方官方说明。
由 HPSILab 根据本条目的端点和软件包,按各客户端官方文档的格式生成。参数、密钥和版本以官方说明为准。
官方说明
# From the official README: https://github.com/datalayer/jupyter-mcp-server
# Jupyter side
pip install jupyterlab jupyter-collaboration jupyter-mcp-tools ipykernel
# MCP client side
{
"mcpServers": {
"jupyter": {
"command": "uvx",
"args": ["jupyter-mcp-server@latest"],
"env": {
"JUPYTER_URL": "http://localhost:8888",
"JUPYTER_TOKEN": "MY_TOKEN",
"ALLOW_IMG_OUTPUT": "true"
}
}
}
}链接
更多「量化研究与风险」类 MCP Server
- Google Colab MCP Server
Let an AI agent work in a Google Colab notebook: add and run cells against Colab's hosted runtimes.
- MATLAB MCP Core Server
MathWorks' server that lets AI agents run MATLAB code and scripts — useful for numerical and quant research.
- arXiv MCP Server
Search, download and read arXiv papers from your AI client — handy for keeping up with quant-finance and ML research.