Programmatic Usage(Python)

MCP with Pydantic AI

Use MCP tools inside Pydantic AI agents

Overview

Pydantic AI has native MCP support via MCPServerStreamableHTTP, allowing agents to automatically discover and invoke tools exposed by your MCP server.


Setup

pip install pydantic-ai mcp

Step 1: Create the MCP Server Abstraction

from pydantic_ai.mcp import MCPServerStreamableHTTP

server = MCPServerStreamableHTTP(
    "https://api.mcphero.app/mcp/{server_id}/mcp",
    headers={"Authorization": "Bearer <your-api-key>"},
)

Step 2: Create an Agent

from pydantic_ai import Agent

agent = Agent(
    "openai:gpt-4o",
    toolsets=[server],
)

Step 3: Run the Agent

async def main():
    result = await agent.run(
        "Find customer John Smith and return their last order"
    )
    print(result.output)

On this page