Use case
Strava AI training analysis
Use KBrain to connect Strava activity data to Claude or ChatGPT through MCP for performance, recovery, route, and training load analysis.
Analyze your Strava training data with KBrain
Subscribe and add StravaStrava records the workouts. KBrain turns them into structured, queryable context. Claude or ChatGPT can then reason across weeks, routes, workouts, and seasons instead of working from one exported file at a time.
What KBrain can surface from Strava
- Performance: heart rate zone distribution, aerobic decoupling, cardiac drift, efficiency factor, cadence patterns
- Route and geography: HR overlays on maps, grade adjusted pace, elevation profiles, repeated route benchmarks
- Training load: HR-based TSS, acute and chronic load (ATL and CTL), form (TSB), overreaching signals
- Cross-activity: running vs cycling fitness transfer, rest-day detection, seasonal performance comparisons
- Health signals: resting HR trends, HRV proxy patterns, anomalous heart rate responses
The point is not that the model becomes your coach. The point is that you can ask normal questions in Claude or ChatGPT and get answers grounded in your actual training history.
What changes when the data is there
Without KBrain, an AI assistant gives generic training advice. With KBrain, it can tell you how much time you actually spent in Zone 2 last month, where your heart rate spikes on your regular route, and whether your easy pace is improving at the same effort. That is a different conversation.
Private by design
Strava data includes location history and health signals. KBrain keeps your training brain private by default, uses read only access, and does not share your data with other users.
Analyze your Strava training data with KBrain
Subscribe to KBrain, add Strava as a private data source, and connect the same training brain to Claude, ChatGPT, or any MCP compatible assistant.
Subscribe and add StravaFrequently asked questions
Can Claude or ChatGPT read Strava directly?
Not by default. KBrain acts as the MCP layer that connects your authorized Strava data to an AI assistant that supports remote MCP connectors.
Does this replace a coach?
No. It helps summarize and analyze training data, but health and training decisions still need human judgment and coaching or medical advice where appropriate.
Which Strava data matters most?
Activity summaries are useful, but the richest analysis comes from streams: time, distance, coordinates, altitude, velocity, heart rate, cadence, watts, and grade.