HAPI Strava MCP Server
Plugs Strava's athlete, activity, segment, club, and route APIs directly into your MCP client without writing integration code. Built on HAPI MCP, which converts OpenAPI specs into MCP tools automatically, so you're calling Strava's production endpoints with auth and rate limits intact. Useful when you're building fitness coaching agents, training log analyzers, or anything that needs to pull workout data, compare segment times, or sync club events into an LLM workflow. Runs as a remote server at strava.run.mcp.com.ai, so no local setup. The HAPI approach means updates to Strava's API surface as new tools without redeploying your agent logic.
- GitHub stars
- 8
- tools
- 10
- transport
- HTTP
- last updated
- Feb 19, 2026
Tools
10 toolsPublic tool metadata for what this MCP can expose to an agent.
get_recent_activitiesGet recent Strava activities (default: last 10)1 params
Get recent Strava activities (default: last 10)
limitnumberget_activity_detailsGet detailed info for a specific activity1 params
Get detailed info for a specific activity
activity_idstringget_weekly_statsWeekly training statistics (distance, time, training load)1 params
Weekly training statistics (distance, time, training load)
weeksnumberget_training_load_analysisAnalyze training load with ATL, CTL, TSB and get REST or TRAIN advice
Analyze training load with ATL, CTL, TSB and get REST or TRAIN advice
No parameter schema in public metadata yet.
get_weekly_training_planGet a weekly plan with recommended hours, workout types and intensities
Get a weekly plan with recommended hours, workout types and intensities
No parameter schema in public metadata yet.
get_gear_maintenanceList all bikes and shoes with total km and maintenance warnings
List all bikes and shoes with total km and maintenance warnings
No parameter schema in public metadata yet.
get_power_curveAnalyze best power outputs (5s, 1min, 5min, 20min, 60min), estimate FTP, and compare with previous month
Analyze best power outputs (5s, 1min, 5min, 20min, 60min), estimate FTP, and compare with previous month
No parameter schema in public metadata yet.
get_hr_zone_distributionAnalyze time spent in each HR zone (last 4 weeks) with training balance advice
Analyze time spent in each HR zone (last 4 weeks) with training balance advice
No parameter schema in public metadata yet.
get_hr_drift_analysisMeasure cardiac drift in steady rides — indicator of aerobic efficiency
Measure cardiac drift in steady rides — indicator of aerobic efficiency
No parameter schema in public metadata yet.
check_workout_qualityAnalyze interval consistency, power decoupling, and recovery for a specific activity1 params
Analyze interval consistency, power decoupling, and recovery for a specific activity
activity_idstringSponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
HAPI MCP – Headless API for Model Context Protocol
Stop rewriting systems for AI. Instantly turn your APIs into MCP servers.
HAPI MCP lifts your OpenAPI catalog into MCP tools automatically, keeping design (OAS/Arazzo) and runtime (agents/LLMs) cleanly separated. Your existing APIs become AI-ready tools—no new business logic, no sidecar servers, no rework.
Key Features
- No rewrites: Reuse 100% of your API logic. OpenAPI in, MCP tools out. No parallel codebase or shadow services.
- Faster time-to-value: Turn specs into agent-ready tools in minutes. Update the spec, ship new tools instantly.
- Reduced risk: Permissions, auth, rate limits, auditability are inherited from your APIs—governance without bolt-ons.
- Scales with you: runMCP delivers serverless-like elasticity with long-running when needed. Cold-start fast, stay warm for throughput.
- Deterministic orchestration: OrcA plans and executes multi-tool tasks predictably—no brittle prompt chaining.
- Vendor-neutral: Works with any MCP client: ChatGPT, Claude, QBot, chatMCP. OAS + MCP + Arazzo stay portable.
Details
- Repository
- github.com/la-rebelion/hapimcp
- Website
- run.mcp.com.ai
- Transport
- HTTP
- Registry
- MCP registry, active