Strava

@strava show my last 5 runs with pace and distance

Here are your last 5 runs: 1. Morning Run (Jan 15) — 5.2 mi at 8:24/mi pace, 312 ft elevation gain 2. Easy Recovery (Jan 13) — 3.1 mi at 9:10/mi pace, 89 ft elevation gain 3. Tempo Run (Jan 11) — 6.8 mi at 7:52/mi pace, 201 ft elevation gain 4. Long Run (Jan 8) — 10.3 mi at 8:45/mi pace, 456 ft elevation gain 5. Hill Repeats (Jan 6) — 4.5 mi at 8:01/mi pace, 612 ft elevation gain This is an illustrative example based on typical Strava activity data structure.

Requires OAuth scope for reading activities. Strava's API returns detailed metrics including splits, heart rate zones, and GPS data if available. Rate limits apply (200 requests per 15 minutes, 2000 per day), so bulk queries may need batching.

@strava log a 3 mile run from this morning at 8:15am, easy effort

Activity created successfully: **Easy Morning Run** Distance: 3.0 miles Start time: Today at 8:15 AM Type: Run Description: Easy effort The activity is now visible on your Strava profile. You can add GPS data, photos, or edit details directly in the Strava app. This example shows a manual activity creation without GPS track data.

Requires OAuth scope for writing activities. Manual entries lack GPS tracks and detailed metrics unless you upload a GPX/TCX file separately. Strava enforces activity type constraints (run, ride, swim, etc.) and won't accept implausible paces or distances.

@strava compare my January mileage to last year and tell me if I'm on track for my 1000-mile annual goal

**January Progress vs. Last Year:** This year: 87.3 miles (15 activities) Last year: 72.1 miles (12 activities) Difference: +15.2 miles (+21%) **Annual Goal Tracking:** Target: 1,000 miles Current pace: 87.3 miles/month → projected 1,048 miles by year-end Status: On track, with 8.3 miles/month buffer You're ahead of schedule. Maintaining this monthly average puts you 4.8% above goal by December. This analysis combines Strava activity data with date-based projections.

Combines activity retrieval with AI reasoning to calculate trends and projections. Accuracy depends on consistent activity logging throughout the year. Strava's API provides aggregate stats, but cross-year comparisons require fetching activities from multiple date ranges, consuming more API quota.

When Strava MCP works for remote team wellness programs

A 12-person remote startup runs monthly step challenges to keep the team connected. The Strava MCP lets you pull activity data into Switchy without asking everyone to screenshot their stats or manually update a spreadsheet. You can query who logged runs this week, compare mileage across departments, or auto-generate leaderboard updates for Slack. The OAuth2 flow means each person authorizes once and you're done. This breaks down if your team uses mixed fitness platforms—Strava won't see Apple Health or Garmin data that never syncs to Strava accounts. If more than half your team is on a different tracker, you'll spend more time reconciling sources than the MCP saves. For Strava-native teams under 20 people, this is the fastest way to automate challenge admin.

How coaches use this MCP for quarterly athlete check-ins

A running coach with eight clients needs to prep quarterly reviews. The Strava MCP pulls each athlete's training log—weekly mileage, pace trends, activity types—into a shared Switchy workspace where the coach drafts feedback. Instead of tabbing between eight Strava profiles and a Google Doc, the coach queries all eight logs in one prompt and spots patterns (like who's skipping recovery runs or ramping volume too fast). The limitation is granularity: Strava's API doesn't expose heart rate zones or power data at the same depth as TrainingPeaks, so if you're coaching cyclists who care about FTP curves, this MCP won't replace your analysis stack. For run-focused coaches working with recreational athletes, it cuts review prep from two hours to twenty minutes.

When race directors use Strava MCP for course validation

A trail race director is scouting a new 50K route and wants to know if local runners already use the segments. The Strava MCP can query segment popularity, elevation profiles, and recent activity counts to validate whether the course is rideable or if certain climbs are too technical for the target field. You pull this data into Switchy, compare it against your permit boundaries, and share annotated maps with your volunteer crew. The catch: Strava's segment data skews toward popular areas. If you're routing through truly remote terrain, the MCP will return sparse results and you'll still need boots-on-ground recon. For events in established trail networks with active Strava users, this MCP turns three weeks of research into a two-day sprint.