SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Bart MCP with Pydantic AI

Connect Pydantic AI to Bart MCP. Find next departures from embarcadero station, get real-time trip updates for richmond line, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Bart logoBart
Api Key

Bart is the Bay Area Rapid Transit system, providing fast public transportation across the San Francisco Bay Area. It helps commuters and travelers get real-time schedule info, plan routes, and stay updated on service changes.

18 Tools

Introduction

This guide walks you through connecting Bart to Pydantic AI using the Composio tool router. By the end, you'll have a working Bart agent that can check real-time departures, plan trips with arrival and departure schedules, look up fares, view service advisories, and check elevator status through natural language commands.

This guide will help you understand how to give your Pydantic AI agent real control over a Bart account through Composio's Bart MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Bart with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIAutoGen

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Bart
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Bart workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

What is the Bart MCP server, and what's possible with it?

The Bart MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Bart account. It provides structured and secure access to BART schedules, fares, routes, stations, and live service information, so your agent can check departures, plan trips, compare fares, monitor advisories, and review station access on your behalf.

  • Real time departure tracking: Have your agent check estimated departures from a chosen BART station and report how many trains are currently active.
  • Trip schedules and fares: Let the agent find scheduled trips by departure or arrival time and compare Clipper and cash fares between stations.
  • Routes and station details: Direct your agent to list BART routes, inspect route schedules, and retrieve detailed station information.
  • Service and elevator updates: Instruct your agent to check current service advisories, trip updates, and elevator status across BART stations.
  • Station access planning: Have your agent review parking, connecting transit, bike facilities, and locker options before your trip.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Bart
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs
5

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Bart
  • MCPServerStreamableHTTP connects to the Bart MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant
6

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Bart
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["bart"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Bart tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
7

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
bart_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[bart_mcp],
    instructions=(
        "You are a Bart assistant. Use Bart tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Bart endpoint
  • The agent uses GPT-5 to interpret user commands and perform Bart operations
  • The instructions field defines the agent's role and behavior
8

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Bart.\n")

while True:
    user_input = input("You: ").strip()
    if user_input.lower() in {"exit", "quit", "bye"}:
        print("\nGoodbye!")
        break
    if not user_input:
        continue

    print("\nAgent is thinking...\n", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Bart API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns
9

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Bart and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Bart
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["bart"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    bart_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[bart_mcp],
        instructions=(
            "You are a Bart assistant. Use Bart tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Bart.\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "bye"}:
            print("\nGoodbye!")
            break
        if not user_input:
            continue

        print("\nAgent is thinking...\n", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've built a Pydantic AI agent that can interact with Bart through Composio's Tool Router. With this setup, your agent can perform real Bart actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Bart for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.
TOOLS

Supported Tools

Every Bart action and event your agent gets out of the box.

Get BART API Version

Get the current version of the BART API.

Get Elevator Status

Tool to fetch current elevator status across all BART stations.

Get Estimated Departures

Tool to get real-time estimated departure times for a specified BART station.

Get BART Fare

Get fare information between two BART stations including Clipper and cash prices.

Get GTFS-RT Service Alerts

Fetch BART GTFS-RT service alerts as protobuf bytes for use with the static GTFS feed.

Get GTFS-RT Trip Updates

Fetch BART GTFS-Realtime trip updates as raw protobuf bytes.

Download GTFS Static Schedule Feed

Fetch the BART static GTFS schedule feed ZIP and return its permalink and the first 1,024 bytes of its content.

Get Route Info

Tool to fetch detailed information about a specific BART route.

Get Route Schedule

Tool to get detailed schedule information for a specific BART route showing all trains and their stops.

Get BART Schedule Arrive

Tool to retrieve schedule information based on a specified arrival time.

Get BART Schedule Depart

Get BART train schedules departing from an origin station to a destination station at a specified time.

Get Service Advisories

Tool to fetch current BART service advisories.

Get Station Access

Get comprehensive station access information including parking, transit, bike facilities, and lockers.

Get Station Info

Get detailed information for a specific BART station by its abbreviation code.

Get BART Stations

Get a list of BART stations with names, abbreviation codes, geographic coordinates, and addresses.

Get Station Schedule

Get detailed scheduled departure information for a specific BART station.

Get Train Count

Tool to fetch current count of trains active in the BART system.

List BART Routes

List BART routes with basic information such as colors, directions, and route numbers.

FRAMEWORKS

How to build Bart MCP Agent with another framework

Claude Code logo

Claude Code

Use Bart MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Bart MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Bart MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Bart MCP with Claude Agent SDK

Codex logo

Codex

Use Bart MCP with Codex

OpenClaw logo

OpenClaw

Use Bart MCP with OpenClaw

Hermes logo

Hermes

Use Bart MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Bart MCP with Atomic Agent

Google ADK logo

Google ADK

Use Bart MCP with Google ADK

LangChain logo

LangChain

Use Bart MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Bart MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Bart MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Bart MCP with LlamaIndex

CrewAI logo

CrewAI

Use Bart MCP with CrewAI

AutoGen logo

AutoGen

Use Bart MCP with AutoGen

FAQ

Frequently asked questions

Start with Bart.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Bart tool your agent needs.Free to start.

Start building