mcpserver.so LogoMCPFly
Submit
MCP Proxy Pydantic Agent logo

MCP Proxy Pydantic Agent

by p2c2e

AI/Agents & IntegrationPydanticPydanticAIAgentsProxy

This example demonstrates how to integrate Model Context Protocol (MCP) servers with Pydantic.AI. It showcases the use of a proxy agent to interact with MCP servers using Pydantic models.

View on GitHub

Last updated: N/A

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

  1. Clone this repo
  2. uv sync
  3. cd mcp-client
  4. uv run client.py (this requires openai and anthropic keys and uses anthropic libs directly)
  5. uv run client2.py (for pure pydantic and works with any fn calling LLM)

(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)