Pydantic AI

Pydantic AI connects to SAN with MCPToolset from pydantic_ai.mcp. Attach it to any Agent through the toolsets argument.

Prerequisites

Python 3.10+
A SAN API key
Create one in the API Quickstart if you don’t have one yet.

Quick Start

Install Pydantic AI with the MCP extra

pip install "pydantic-ai-slim[mcp]"

Point a toolset at SAN

A URL without an /sse suffix uses streamable HTTP. Pass your key in headers.

from pydantic_ai.mcp import MCPToolset

server = MCPToolset(
    'https://playground.sanfoundation.com/mcp',
    headers={'x-api-key': 'sk_...'},
)

On Pydantic AI 1.x this was a separate class, MCPServerStreamableHTTP. Version 2.0 replaced the per-transport server classes with the unified MCPToolset — the url and headers arguments work the same, though some defaults changed.

Run an agent with SAN's tools

Pass the toolset via toolsets and open the agent to manage the connection.

import asyncio
from pydantic_ai import Agent

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

async def main() -> None:
    async with agent:
        result = await agent.run('Which SAN agents are available?')
        print(result.output)

asyncio.run(main())

Getting started

Integrations

Pydantic AI

Prerequisites

Quick Start

​Prerequisites

​Quick Start

Prerequisites

Quick Start