Connect your AI Agents to Strava in minutes

What is a Strava MCP?

It's an MCP server that gives your agents direct access to Strava's fitness and activity data via tools. Your agents can invoke these tools to retrieve athlete activities, fetch performance stats, explore route segments, manage club memberships, and more.

Strava doesn't offer an MCP server purpose built for Strava, but you can use one from a third-party platform, like Merge Agent Handler.

How can I use the Strava MCP server?

The use cases naturally depend on the agent you've built, but here are a few common ones:

• Post-workout coaching digest: After an athlete completes an activity, an agent fetches the activity streams (pace, heart rate, and power) and historical stats from Strava, then sends a personalized performance summary to the athlete via email or Slack

• Weekly training volume report: An agent pulls the past 7 days of activities from Strava, compares total mileage against a training plan stored in a spreadsheet, and generates a summary for a coach or training app

• Segment discovery for route planning: When a user enters a new region, an agent calls Strava to explore nearby segments ranked by popularity, then adds the top picks to a connected route planning or mapping tool

• Club activity leaderboard: An agent pulls recent activities from Strava club members, identifies who logged a workout in the past 24 hours, and posts a daily leaderboard to the club's Slack or Discord channel

What are popular tools for Strava's MCP server?

Here are some of the most commonly used tools:

• list_athlete_activities: returns a paginated list of activities for the authenticated athlete, sorted by date. Useful for agents that need to scan recent workouts as part of a reporting or coaching workflow

• get_activity: retrieves full details for a single activity, including distance, elapsed time, elevation, and gear. Call this when an agent needs granular activity data to power a summary or comparison

• get_activity_streams: fetches raw time-series data for an activity, including pace, heart rate, power output, and cadence. Good for workflows that need to analyze performance at a per-second resolution

• get_athlete_stats: pulls lifetime and recent totals for the authenticated athlete, covering total distance run, ridden, or swum. Helpful when an agent needs a high-level performance overview rather than individual activity records

• explore_segments: searches for Strava segments within a map bounds area, filterable by activity type. Use this when an agent is building route recommendations or identifying competitive benchmarks in a given region

• create_activity: logs a manual activity entry against the athlete's account with fields like type, distance, and duration. Use this when an agent needs to record an activity sourced from an external device or system that doesn't sync automatically

What makes Merge Agent Handler's Strava MCP server better than alternative Strava MCP servers?

Merge Agent Handler's Strava MCP server has a few distinct advantages over rolling your own or relying on an alternative:

• Enterprise-grade security and DLP: Merge Agent Handler includes built-in data loss prevention controls that let you block or redact sensitive fields before they reach an agent. For Strava, this means you can prevent athlete health data, location history, and personal performance records from being exposed even when the agent has broad read access

• Managed authentication and credentials: Merge stores and refreshes Strava OAuth tokens on your behalf. You never hand raw credentials to an agent or build your own token refresh logic

• Real-time observability and audit trail: Every tool call made against Strava is logged with timestamp, tool name, input parameters, and response metadata. You can review exactly what an agent read or wrote without adding any instrumentation to your own code

• Tool Packs and controlled access: Tool Packs let you bundle specific Strava tools with tools from other connectors into a single MCP endpoint, scoped to a specific use case. An agent gets exactly the tools it needs, nothing more

How can I start using Merge Agent Handler's Strava MCP server?

You can take the following steps:

1. Create or log into your Merge Agent Handler account and navigate to Tool Packs (collections of connector tools scoped to a specific use case).

2. Create a new Tool Pack, then find and enable the Strava connector. Choose which tools to include: enable read tools like list_athlete_activities and get_athlete_stats for analysis and reporting, or add write tools like create_activity and update_activity if your agent needs to log or modify activity records.

3. Add a Registered User inside the Tool Pack. This is the identity context under which your agent operates. Merge generates a unique MCP URL scoped to this user once it's created.

4. From the Registered User detail page, authenticate Strava by completing the OAuth flow. Merge stores and manages the credentials going forward.

5. Copy the MCP URL from the Tool Pack detail page and generate an API key from Settings. You'll need both to connect your agent.

6. Add the MCP server to your agent or IDE using the MCP URL and API key. Your Strava tools are now accessible through that endpoint.