Strava Social MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Strava Social through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token — get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="Strava Social Assistant",
instructions=(
"You help users interact with Strava Social. "
"You have access to 10 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Strava Social"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Strava Social MCP Server
Connect Strava Social to any AI agent and explore the social side of Strava — activity feeds, kudos, comments, club memberships, and segment discovery.
The OpenAI Agents SDK auto-discovers all 10 tools from Strava Social through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Strava Social, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.
What you can do
- Activity Feed — Browse your recent activities with full details, kudos counts, and comment counts
- Activity Comments — Read all comments on any activity with author names and text
- Activity Kudos — See who liked/supports your activities with full athlete profiles
- Athlete Profile — Get your Strava profile details including location, follower counts, and equipment
- Club Membership — List all clubs you belong to with member counts and sport types
- Club Details — Explore any club's description, location, and community focus
- Club Members — Browse club membership to find training partners and local athletes
- Club Activities — See what club members have been doing recently
- Starred Segments — Review all your favorited segments with PR times and characteristics
- Segment Discovery — Explore segments in any geographic area by bounding box, filterable by type and difficulty
The Strava Social MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Strava Social to OpenAI Agents SDK via MCP
Follow these steps to integrate the Strava Social MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 10 tools from Strava Social
Why Use OpenAI Agents SDK with the Strava Social MCP Server
OpenAI Agents SDK provides unique advantages when paired with Strava Social through the Model Context Protocol.
Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Strava Social + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Strava Social MCP Server delivers measurable value.
Automated workflows: build agents that query Strava Social, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents — one queries Strava Social, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Strava Social tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Strava Social to resolve tickets, look up records, and update statuses without human intervention
Strava Social MCP Tools for OpenAI Agents SDK (10)
These 10 tools become available when you connect Strava Social to OpenAI Agents SDK via MCP:
explore_segments
g., "-74.00,40.70,-73.95,40.75" for Manhattan). Optional filters: activity_type ("running" or "riding"), min_cat/max_cat (category 0-5, where 0 is hardest/steepest). Returns segments with name, distance, elevation, grade, and climb category. Use this to discover new training routes, find popular segments in an area, or plan rides/runs in a new city. Explore and discover Strava segments in a geographic area
get_activity_comments
Each comment includes athlete name, text, and creation date. The activityId is the numeric ID from Strava activity URLs. Use this to see community engagement on a workout, read feedback, or track conversation around a specific activity. Get all comments on a specific Strava activity
get_activity_kudos
Each entry includes athlete name, profile picture, and city. The activityId is the numeric ID from Strava. Use this to see who supported an activity, understand social engagement, or track training partners' interactions. Get the list of athletes who gave kudos (likes) to a specific activity
get_athlete
Use this to understand the athlete's identity, location, and equipment setup. Get the authenticated athlete's profile information
get_club
The clubId is found in Strava club URLs. Use this to explore club details before joining or to understand a club's focus and community. Get detailed information about a specific Strava club
list_activities
Activities are sorted by most recent first. Optional filters: "before" (epoch timestamp, defaults to now), "after" (epoch timestamp for date range), "page" and "per_page" (pagination, max 200 per page, max 2000 total). Each activity includes: name, type, distance, moving_time, elevation, kudos_count, comment_count, start_date, and basic stats. Use this to get the activity feed, analyze recent workouts, or review training history. Epoch timestamps can be generated from dates. List the authenticated athlete's activities with optional date filtering and pagination
list_athlete_clubs
Each club includes name, member count, city, country, sport type (cycling/running/triathlon), and privacy status. Use this to discover club memberships, find training groups, or understand community affiliations. List all clubs the authenticated athlete belongs to
list_club_activities
Each entry includes athlete name, activity name, type, distance, and date. Paginated (30 per page). The clubId is from Strava club URLs. Use this to stay updated on club training activity, discover what members are doing, or find group workout opportunities. Get recent activities from members of a Strava club
list_club_members
Paginated (30 per page). The clubId is from Strava club URLs. Use this to discover training partners in a club, find athletes in your area, or explore club community composition. List members of a specific Strava club
list_starred_segments
Each segment includes: name, distance, elevation gain, average grade, activity type, city, country, and the athlete's PR time if any. Use this to review favorite segments, plan training routes, or track progress on key segments over time. List all segments starred (favorited) by the authenticated athlete
Example Prompts for Strava Social in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Strava Social immediately.
"Show my recent activities."
"Explore cycling segments in Manhattan, NYC."
"Show comments on my latest activity."
Troubleshooting Strava Social MCP Server with OpenAI Agents SDK
Common issues when connecting Strava Social to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Strava Social + OpenAI Agents SDK FAQ
Common questions about integrating Strava Social MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Strava Social with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Strava Social to OpenAI Agents SDK
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.