Content
# MCP demo (DeepSeek as Client's LLM)
## How to run
1. Config `.env` file
Add `.env` file in project root and add DeepSeek api key:
```
# DeepSeek
DEEPSEEK_API_KEY=
```
2. Run MCP Client & Server
```
$ pip install -r requirements.txt
$ python client.py weather.py
```
## Reference
1. <https://github.com/modelcontextprotocol/quickstart-resources/tree/main/mcp-client-python>
2. [基于DeepSeek-V3开发MCP天气查询智能体_python_深圳dengdi-DeepSeek技术社区](https://deepseek.csdn.net/67dfc6128393e26e2657ddc8.html)
Connection Info
You Might Also Like
markitdown
MarkItDown-MCP is a lightweight server for converting URIs to Markdown.
servers
Model Context Protocol Servers
Time
A Model Context Protocol server for time and timezone conversions.
Filesystem
Node.js MCP Server for filesystem operations with dynamic access control.
Sequential Thinking
A structured MCP server for dynamic problem-solving and reflective thinking.
git
A Model Context Protocol server for Git automation and interaction.