mcp_proxy_pydantic_agent
Language:
Python
Stars:
14
Forks:
5
Sample to show to integrate MCP (Model Context Protocol) servers with Pydantic.AI
Parts of this example uses content from : https://github.com/modelcontextprotocol/quickstart-resources.git - Esp. the weather 'server' code
Code uses two different LLMs just for demonstration. The Proxy Agent uses gpt-4o and the tool uses sonnet. So, export OPENAI_API_KEY as well as ANTHROPIC_API_KEY - OR - modify the code to suit your models
The pyproject.toml assumes you are using 'uv' package manager
Steps to run
- Clone this repo
- uv sync
- cd mc-client
- uv run client.py
(Alternatively try client2.py - this uses only PydanticAI - no direct dep on Anthropic libs)
Now, try interacting with some questions like:
What is the time in NY when it is 7:30pm in Bangalore?
What is the Weather currently in Chicago?
(and quit when done)
Publisher info
More MCP servers built with Python
An MCP (Model Context Protocol) server that provides access to Bing Webmaster Tools functionality
This MCP server provides access to real-time water data from the USGS Water Services API. It allows you to fetch instantaneous water measurements including stream flow, gage height, temperature, and other water quality parameters from thousands of monitoring stations across the United States.