Strava MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_recent_activitiesB | Get recent Strava activities (default: last 10) |
| get_activity_detailsA | Get detailed info for a specific activity |
| get_weekly_statsB | Weekly training statistics (distance, time, training load) |
| get_training_load_analysisA | Analyze training load with ATL, CTL, TSB and get REST or TRAIN advice |
| get_weekly_training_planA | Get a weekly plan with recommended hours, workout types and intensities based on your current status |
| get_gear_maintenanceA | List all bikes and shoes with total km and maintenance warnings |
| get_power_curveA | Analyze best power outputs (5s, 1min, 5min, 20min, 60min), estimate FTP, and compare with previous month |
| get_hr_zone_distributionA | Analyze time spent in each HR zone (last 4 weeks) with training balance advice |
| get_hr_drift_analysisA | Measure cardiac drift in steady rides — indicator of aerobic efficiency |
| check_workout_qualityA | Analyze interval consistency, power decoupling, and recovery for a specific activity |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Each tool targets a distinct analysis or information retrieval function, such as workout quality, gear maintenance, heart rate drift, power curve, and training load. No two tools have overlapping purposes, making it clear which tool to use for a given query.
All tools follow a verb_noun pattern using snake_case, with most starting with 'get'. One tool uses 'check' instead of 'get', and a few use abbreviations like 'hr' and 'stats', but these are minor deviations that don't affect readability.
With 10 tools, the set is well-scoped for a Strava analysis server covering key metrics like heart rate, power, training load, and gear maintenance. It's not too many to be overwhelming nor too few to be trivial.
The tool set comprehensively covers training analytics (HR, power, load, weekly stats, planning) and basic activity retrieval. Minor gaps exist, such as no tool for updating activity details or managing goals, but the core analysis workflows are well-supported.