SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Strava MCP with Pydantic AI

Connect Pydantic AI to Strava MCP. Get your latest cycling activity stats, list all runs i logged this week, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Strava logoStrava
Oauth2

Strava is a social fitness network and app for cyclists and runners. It's perfect for tracking workouts, sharing progress, and joining active communities.

36 Tools

Introduction

This guide walks you through connecting Strava to Pydantic AI using the Composio tool router. By the end, you'll have a working Strava agent that can upload and create activities, review activity details and laps, explore segments, export routes as GPX, and check your athlete stats through natural language commands.

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

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

Also integrate Strava with

Claude CodeCursorChatGPTClaude CoworkAntigravityOpenAI Agents SDKClaude Agent SDKCodexGrok BuildVS CodeOpenCodeOpenClawHermesAtomic 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 Strava
  • 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 Strava 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 Strava MCP server, and what's possible with it?

The Strava MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Strava account. It provides structured and secure access to your fitness data, so your agent can perform actions like fetching activities, analyzing stats, logging workouts, managing routes, and exploring your social fitness feed on your behalf.

  • Workout tracking and retrieval: Let your agent pull detailed records of your recent runs, rides, and other logged activities, complete with stats, maps, and performance data.
  • Fitness analytics and progress insights: Have your agent analyze your weekly or monthly trends, highlight PRs, and summarize progress toward your training goals.
  • Route exploration and management: Ask your agent to list, suggest, or organize your favorite routes and segments for upcoming workouts or challenges.
  • Social engagement automation: Enable your agent to fetch kudos, summarize comments, or surface activity highlights from friends and clubs in your Strava network.
  • Activity creation and editing: Allow your agent to log new activities, edit workout details, or update activity metadata for accurate record keeping.

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 Strava
  • 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 Strava
  • MCPServerStreamableHTTP connects to the Strava 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 Strava
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["strava"],
    )
    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 Strava 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
strava_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[strava_mcp],
    instructions=(
        "You are a Strava assistant. Use Strava tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Strava endpoint
  • The agent uses GPT-5 to interpret user commands and perform Strava 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 Strava.\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
  • Strava 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 Strava 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 Strava
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["strava"],
    )
    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
    strava_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[strava_mcp],
        instructions=(
            "You are a Strava assistant. Use Strava 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 Strava.\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 Strava through Composio's Tool Router. With this setup, your agent can perform real Strava 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 + Strava 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 Strava action and event your agent gets out of the box.

Get Activity Laps

Retrieves lap data for a specific Strava activity by its identifier.

Create an Activity

Creates a manual activity for an athlete.

Explore segments

Explore the top 10 segments within a geographic bounding box, with optional activity type and climbing-category filters.

Export Route as GPX

Exports a Strava route as a GPX (GPS Exchange Format) file.

Export Route as TCX

Exports a Strava route as a TCX (Training Center XML) file.

Get Activity

Retrieves detailed information about a specific activity by its ID.

Get activity streams

Retrieves time-series stream data for a specific activity.

Get Activity Zones

Returns the heart rate and power zones of a given activity.

Get athlete stats

Retrieves activity statistics for the authenticated athlete by athlete ID, including recent, year-to-date, and all-time ride, run, and swim totals.

Get athlete zones

Retrieves the authenticated athlete's heart rate and power training zones for reviewing their configured zone ranges.

Get authenticated athlete

Retrieves the profile of the currently authenticated Strava athlete.

Get Club

Retrieves detailed information about a specific Strava club by its ID.

Get equipment

Retrieves detailed information about a specific piece of gear/equipment.

Get route

Retrieve detailed information about a specific Strava route.

Get route streams

Get detailed stream data for a route.

Get segment

Retrieve detailed information about a Strava segment, including geographic and map data, aggregate statistics, and athlete-specific records when available.

Get segment effort

Retrieve a segment effort by ID from an activity owned by the authenticated athlete, with performance details such as elapsed time, distance, heart rate, power, and cadence when available.

Get segment effort streams

Returns stream data for a segment effort completed by the authenticated athlete.

Get segment streams

Get detailed stream data for a segment.

Get Upload Status

Retrieves the status of an upload by its ID.

Get zones

Retrieves the authenticated athlete's heart rate and power training zones for reviewing their configured zone ranges.

List activity comments

Retrieves comments on a specific Strava activity, sorted oldest first.

List activity kudoers

Returns the athletes who kudoed an activity identified by an identifier.

List activity laps

Retrieves lap data for a specific Strava activity.

List athlete activities

Retrieves a paginated list of activities for the authenticated athlete.

List athlete clubs

Retrieves a paginated list of Strava clubs the authenticated athlete is a member of.

List athlete routes

Lists routes created by a specific athlete.

List club activities

Retrieve recent activities from members of a specific club.

List club administrators

Returns a list of the administrators of a given Strava club.

List club members

Returns a list of the athletes who are members of a given club.

List segment efforts

List the authenticated athlete's segment efforts for a specified segment, optionally filtered by date range and limited by page size.

List starred segments

Returns a list of the authenticated athlete's starred segments with summary details including segment name, distance, elevation, grade, and location.

Star segment

Stars/Unstars the given segment for the authenticated athlete.

Update Athlete

Update the currently authenticated athlete's profile.

Upload Activity

Uploads a new activity file (FIT, TCX, or GPX) to create an activity on Strava.

Validate credential

Validates Strava API credentials by fetching the authenticated athlete's profile.

FRAMEWORKS

How to build Strava MCP Agent with another framework

Claude Code logo

Claude Code

Use Strava MCP with Claude Code

Cursor logo

Cursor

Use Strava MCP with Cursor

ChatGPT logo

ChatGPT

Use Strava MCP with ChatGPT

Claude Cowork logo

Claude Cowork

Use Strava MCP with Claude Cowork

Antigravity logo

Antigravity

Use Strava MCP with Antigravity

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Strava MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Strava MCP with Claude Agent SDK

Codex logo

Codex

Use Strava MCP with Codex

Grok Build logo

Grok Build

Use Strava MCP with Grok Build

VS Code logo

VS Code

Use Strava MCP with VS Code

OpenCode logo

OpenCode

Use Strava MCP with OpenCode

OpenClaw logo

OpenClaw

Use Strava MCP with OpenClaw

Hermes logo

Hermes

Use Strava MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Strava MCP with Atomic Agent

Google ADK logo

Google ADK

Use Strava MCP with Google ADK

LangChain logo

LangChain

Use Strava MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Strava MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Strava MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Strava MCP with LlamaIndex

CrewAI logo

CrewAI

Use Strava MCP with CrewAI

AutoGen logo

AutoGen

Use Strava MCP with AutoGen

FAQ

Frequently asked questions

With a standalone Strava MCP server, the agents and LLMs can only access a fixed set of Strava tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Strava and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Pydantic AI fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Strava tools.

Yes, absolutely. You can configure which Strava scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Strava data and credentials are handled as safely as possible.

Start with Strava.It takes 30 seconds.

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

Start building