Strava gives Claude access to your entire training history
The new integration gives subscribers a way to ask natural-language questions about their workouts in Claude
Strava has announced a new AI-powered feature that allows subscribers to connect their accounts directly to Claude, the AI assistant developed by Anthropic.
The new Model Context Protocol (MCP) connector is rolling out globally this week and enables you to ask questions about your training history in natural language.
According to Strava, the integration can access activity data, including heart rate, pace, GPS data, cycling power metrics, clubs, and events.
The launch makes Strava one of the first major fitness platforms to offer a native integration with an external AI assistant, giving subscribers a new way to explore the data they've accumulated over months or even years of training.
A different role to Athlete Intelligence
The announcement arrives less than two years after Strava introduced Athlete Intelligence, its AI-powered feature that generates summaries and insights for individual activities.
While both features use AI, they are designed for different purposes.
Athlete Intelligence focuses on explaining what happened during a specific workout, highlighting notable efforts, pacing trends and other key takeaways after an activity has been completed.
Get all the latest news, reviews, deals and buying guides on gorgeous tech, home and active products from the T3 experts
The new Claude integration is more conversational, allowing you to ask your own questions about your training history and receive responses based on data stored in your Strava account.
Strava suggests subscribers could ask questions such as "Are my easy days easy enough?" or "How is my cross-training affecting my running?"
Making training data easier to explore
According to Strava, athletes have already been using exports, spreadsheets and third-party tools to analyse their training history with AI assistants.
The MCP connector is intended to simplify that process by creating a direct connection between Strava and Claude.
The company says the integration provides read-only access to user data and can be revoked at any time through Strava settings.
Ryan Dixon, Vice President of Partnerships & Developer Relations at Strava, said athletes have been looking for new ways to analyse their training data for years.
"The MCP connector gives them a far more efficient, safer tool while keeping the athlete in control," Dixon said.
As with any AI integration that accesses personal data, you will likely want to review the permissions involved before connecting your account, particularly given the amount of location, performance and health-related information stored within Strava histories.
The Strava MCP connector is available to subscribers and is now rolling out globally. Setup instructions are available through Strava's Help Centre.

Matt Kollat is a journalist and content creator for T3.com and T3 Magazine, where he works as Active Editor. His areas of expertise include wearables, drones, action cameras, fitness equipment, nutrition and outdoor gear. He joined T3 in 2019.
His work has also appeared on TechRadar and Fit&Well, and he has collaborated with creators such as Garage Gym Reviews. Matt has served as a judge for multiple industry awards, including the ESSNAwards. When he isn’t running, cycling or testing new kit, he’s usually roaming the countryside with a camera or experimenting with new audio and video gear.
You must confirm your public display name before commenting
Please logout and then login again, you will then be prompted to enter your display name.