Strava MCP Server
Provides tools for interacting with the Strava API v3, allowing management of activities, athletes, clubs, segments, routes, streams, gear, and more.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Strava MCP Server What was my total running distance last week?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Strava MCP Server
A Model Context Protocol (MCP) server that provides full access to the Strava API v3. Connect Claude (or any MCP client) to your Strava fitness data — activities, athletes, clubs, segments, routes, streams, gear, and more.
Features
30+ tools covering all major Strava API v3 endpoints
Auto token refresh — OAuth2 tokens are refreshed and cached automatically
Formatted responses — distances in km, times in minutes, speeds in km/h
Convenience tools — weekly/monthly summaries, filter by sport type
Available Tools
Category | Tools |
Activities | Create, get details, comments, kudos, laps, list, zones, update |
Athletes | Profile, zones, stats, update weight |
Clubs | List, details, members, admins, activities |
Gear | Get gear details (bikes & shoes) |
Routes | List, details, GPX export, TCX export |
Segments | Explore, starred, details, star/unstar |
Segment Efforts | List efforts, effort details |
Streams | Activity, route, effort, segment time-series data |
Uploads | Upload status |
Summaries | Weekly summary, monthly summary, filter by sport type, filter by date |
Related MCP server: Strava MCP Server
Prerequisites
Python 3.12+
uv (Python package manager)
A Strava account
A Strava API application (see setup below)
Setup
1. Create a Strava API Application
Create a new application:
Application Name: anything (e.g. "MCP Server")
Category: choose any
Website:
http://localhostAuthorization Callback Domain:
localhost
Note your Client ID and Client Secret
2. Clone and Install
git clone https://github.com/manojanasuri16/strava-mcp-server.git
cd strava-mcp-server
uv sync3. Configure Environment
Create a .env file in the project root:
STRAVA_CLIENT_ID=<your_client_id>
STRAVA_CLIENT_SECRET=<your_client_secret>
STRAVA_REFRESH_TOKEN=<your_refresh_token>To get your refresh token, follow the OAuth Authorization steps below.
4. OAuth Authorization (Getting Your Refresh Token)
Strava uses OAuth2. You need to authorize the app once to get a refresh token.
Step 1: Authorize in browser
Open this URL in your browser (replace YOUR_CLIENT_ID):
https://www.strava.com/oauth/authorize?client_id=YOUR_CLIENT_ID&response_type=code&redirect_uri=http://localhost&scope=read_all,activity:read_all,activity:write,profile:read_all,profile:writeStep 2: Grab the authorization code
After you click "Authorize", Strava redirects to:
http://localhost?code=AUTHORIZATION_CODE&scope=...Copy the code value from the URL. This code is single-use and expires in minutes, so proceed quickly.
Step 3: Exchange code for tokens
On Linux/macOS (bash):
curl -X POST https://www.strava.com/api/v3/oauth/token \
-d client_id=YOUR_CLIENT_ID \
-d client_secret=YOUR_CLIENT_SECRET \
-d code=AUTHORIZATION_CODE \
-d grant_type=authorization_codeOn Windows (PowerShell):
Invoke-RestMethod -Method Post -Uri "https://www.strava.com/api/v3/oauth/token" -Body @{
client_id = "YOUR_CLIENT_ID"
client_secret = "YOUR_CLIENT_SECRET"
code = "AUTHORIZATION_CODE"
grant_type = "authorization_code"
}Step 4: Save the refresh token
The response will include access_token, refresh_token, and expires_at. Copy the refresh_token value into your .env file.
The server will automatically refresh the access token when it expires using this refresh token.
Usage
Test with MCP Inspector
The MCP Inspector provides a web UI to test your tools:
uv run mcp dev strava_server.pyOpen the Inspector URL shown in the terminal
Click Connect
Go to the Tools tab
Try running a tool like
get_athlete_profileorget_recent_activities
Use with Claude Code (CLI)
From your project directory, register the server:
claude mcp add strava -- uv run strava_server.pyThen start a new Claude Code session and ask things like:
"How was my running this week?"
"Show me my last 10 activities"
"What are my all-time cycling stats?"
"Find popular running segments near Bangalore"
"Create a manual yoga activity for today"
Use with Claude Desktop
uv run mcp install strava_server.pyOr manually add to your config file:
Windows:
%APPDATA%\Claude\claude_desktop_config.jsonmacOS:
~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"strava": {
"command": "uv",
"args": ["run", "strava_server.py"],
"cwd": "/path/to/strava-mcp-server"
}
}
}Restart Claude Desktop after saving.
Use with ChatGPT Desktop
Open ChatGPT Desktop app
Go to Settings > MCP
Add a new server with:
Name:
stravaCommand:
uv run strava_server.pyWorking directory:
/path/to/strava-mcp-server
Restart ChatGPT Desktop after adding.
Use with Cursor / VS Code
Add to .cursor/mcp.json or .vscode/mcp.json in your workspace:
{
"servers": {
"strava": {
"command": "uv",
"args": ["run", "strava_server.py"],
"cwd": "/path/to/strava-mcp-server"
}
}
}Run Standalone
uv run strava_server.pyTroubleshooting
401 Unauthorized Error
This is the most common issue. It means your access token is invalid.
Cause 1: Stale cached tokens
The server caches tokens at ~/.strava-mcp-tokens.json. If this file contains expired/invalid tokens, the server will keep using them.
Fix:
# Linux/macOS
rm ~/.strava-mcp-tokens.json
# Windows (PowerShell)
Remove-Item "$HOME\.strava-mcp-tokens.json" -ErrorAction SilentlyContinueThen restart the server.
Cause 2: Invalid refresh token
Your refresh token in .env may be expired or revoked. This happens if:
You re-authorized the app and got a new refresh token (old one is invalidated)
You revoked the app's access in Strava settings
The token was never obtained properly
Fix: Redo the OAuth Authorization steps to get a fresh refresh token.
Cause 3: Wrong client credentials
Double-check your STRAVA_CLIENT_ID and STRAVA_CLIENT_SECRET in .env match what's shown at https://www.strava.com/settings/api.
429 Rate Limit
Strava limits API requests to:
100 requests per 15 minutes
1,000 requests per day
The server returns a helpful error message when rate-limited. Wait a few minutes and try again.
Token Refresh Fails on Startup
If the server crashes immediately with a token error, make sure:
Your
.envfile exists in the project rootAll three variables are set (
STRAVA_CLIENT_ID,STRAVA_CLIENT_SECRET,STRAVA_REFRESH_TOKEN)There are no extra spaces or quotes around the values
Missing Scopes
Some tools require specific OAuth scopes:
activity:read_all— needed for activity details, streamsactivity:write— needed for creating/updating activitiesprofile:read_all— needed for athlete zonesprofile:write— needed for updating weight
If a tool returns a 403 Forbidden error, you may need to re-authorize with the correct scopes. Use the authorization URL in Step 1 above (it includes all scopes).
Project Structure
strava-mcp-server/
├── strava_server.py # Entry point (thin wrapper)
├── src/
│ └── strava_mcp/
│ ├── __init__.py # Package exports
│ ├── server.py # FastMCP instance & logging
│ ├── auth.py # OAuth2 token management
│ ├── client.py # HTTP helpers (GET, POST, PUT)
│ ├── formatters.py # Response formatting utilities
│ └── tools/
│ ├── __init__.py # Auto-imports all tool modules
│ ├── activities.py # Activity CRUD, laps, zones, comments, kudos
│ ├── athletes.py # Profile, stats, zones, weight
│ ├── clubs.py # Clubs, members, admins, activities
│ ├── gear.py # Bike & shoe details
│ ├── routes.py # Routes, GPX/TCX export
│ ├── segments.py # Segments, efforts, explore, star
│ ├── streams.py # Time-series data streams
│ └── extras.py # Summaries, filters, upload status
├── pyproject.toml # Project config and dependencies
├── uv.lock # Locked dependencies
├── .env # Your Strava credentials (not committed)
└── README.md # This fileLicense
MIT
Available Tools
37 toolscreate_activityA
Create a manual activity on Strava. Requires activity:write scope.
Args: name: The name of the activity. sport_type: Sport type, e.g. Run, Ride, Swim, Hike, Walk, MountainBikeRide, GravelRide, TrailRun, Yoga, WeightTraining, Workout, etc. start_date_local: Start time in ISO 8601 format (e.g. 2025-03-07T08:00:00). elapsed_time: Total elapsed time in seconds. description: Optional description. distance: Distance in meters. Optional for non-GPS activities. trainer: Set True if this is a trainer/indoor activity. commute: Set True if this is a commute.
Inputs: name (required), sport_type (required), start_date_local (required), elapsed_time (required), +4 more.
explore_segmentsA
Find popular segments within a geographic bounding box.
Args: south_west_lat: South-west corner latitude. south_west_lng: South-west corner longitude. north_east_lat: North-east corner latitude. north_east_lng: North-east corner longitude. activity_type: "riding" or "running" (default "riding"). min_cat: Minimum climb category 0-5 (default 0). max_cat: Maximum climb category 0-5 (default 5).
Inputs: south_west_lat (required), south_west_lng (required), north_east_lat (required), north_east_lng (required), +3 more. Returns: result
export_route_gpxB
Export a route as GPX XML data for use in GPS devices or other apps.
Args: route_id: The Strava route ID.
Inputs: route_id (required). Returns: result
export_route_tcxC
Export a route as TCX XML data for use in GPS devices or other apps.
Args: route_id: The Strava route ID.
Inputs: route_id (required). Returns: result
get_activities_by_dateA
Get activities within a specific date range.
Args: after: Start date in YYYY-MM-DD format (inclusive). before: End date in YYYY-MM-DD format (inclusive). count: Max activities to return (1-200, default 50).
Inputs: after (required), before (required), count. Returns: result
get_activities_by_typeA
Get recent activities filtered by sport type.
Args: sport_type: Run, Ride, Swim, Walk, Hike, TrailRun, MountainBikeRide, GravelRide, VirtualRide, Yoga, etc. count: Number of recent activities to search through (max 200).
Inputs: sport_type (required), count. Returns: result
get_activityA
Get full details for a specific activity including splits, segment efforts, laps, gear, description, and map data.
Args: activity_id: The numeric Strava activity ID. include_all_efforts: If True, include all segment efforts (not just notable ones).
Inputs: activity_id (required), include_all_efforts.
get_activity_commentsA
Get comments on a specific activity.
Args: activity_id: The Strava activity ID. page_size: Number of comments per page (default 30).
Inputs: activity_id (required), page_size. Returns: result
get_activity_kudoersC
Get the list of athletes who gave kudos on an activity.
Args: activity_id: The Strava activity ID. page: Page number (default 1). per_page: Items per page (default 30).
Inputs: activity_id (required), page, per_page. Returns: result
get_activity_lapsA
Get lap-by-lap breakdown for a specific activity. Useful for interval workouts and structured training sessions.
Args: activity_id: The numeric Strava activity ID.
Inputs: activity_id (required). Returns: result
get_activity_streamsA
Get time-series stream data for an activity. Returns arrays of second-by-second data for heart rate, speed, power, cadence, altitude, GPS coordinates, temperature, and grade.
Args: activity_id: The Strava activity ID. keys: Comma-separated stream types. Available: time, distance, latlng, altitude, velocity_smooth, heartrate, cadence, watts, temp, moving, grade_smooth. Defaults to all.
Inputs: activity_id (required), keys.
get_activity_zonesA
Get heart rate and power zones for a specific activity. Shows time spent in each zone. Requires Strava Summit.
Args: activity_id: The Strava activity ID.
Inputs: activity_id (required). Returns: result
get_athlete_profileA
Get the authenticated athlete's full Strava profile. Returns name, bio, location, weight, FTP, bikes, shoes, premium status, and measurement preferences.
Inputs: no named parameters.
get_athlete_statsA
Get all-time and recent statistics for the authenticated athlete. Includes totals for running, cycling, and swimming broken down by recent (last 4 weeks), year-to-date, and all-time.
Inputs: no named parameters.
get_athlete_zonesA
Get the authenticated athlete's heart rate and power zones. Returns zone boundaries and distribution data. Requires profile:read_all scope.
Inputs: no named parameters. Returns: result
get_clubC
Get detailed information about a specific club.
Args: club_id: The Strava club ID.
Inputs: club_id (required).
get_club_activitiesB
List recent activities posted by members of a specific club.
Args: club_id: The Strava club ID. page: Page number (default 1). per_page: Items per page (default 30).
Inputs: club_id (required), page, per_page. Returns: result
get_club_adminsB
List administrators of a specific club.
Args: club_id: The Strava club ID. page: Page number (default 1). per_page: Items per page (default 30).
Inputs: club_id (required), page, per_page. Returns: result
get_club_membersB
List members of a specific club.
Args: club_id: The Strava club ID. page: Page number (default 1). per_page: Items per page (default 30).
Inputs: club_id (required), page, per_page. Returns: result
get_gearB
Get details about a specific piece of gear (bike or shoes). Gear IDs start with 'b' for bikes and 'g' for shoes.
Args: gear_id: The gear ID (e.g. "b12345" for a bike, "g12345" for shoes).
Inputs: gear_id (required).
get_my_clubsA
List all clubs the authenticated athlete is a member of.
Args: page: Page number (default 1). per_page: Items per page (default 30).
Inputs: page, per_page. Returns: result
get_my_routesA
List the authenticated athlete's saved routes.
Args: page: Page number (default 1). per_page: Items per page (default 30).
Inputs: page, per_page. Returns: result
get_recent_activitiesA
Get the most recent activities from your Strava account.
Args: count: Number of activities to return (1-200, default 10).
Inputs: count. Returns: result
get_routeC
Get detailed information about a specific route.
Args: route_id: The Strava route ID.
Inputs: route_id (required).
get_route_streamsC
Get stream data for a route (distance, altitude, latlng).
Args: route_id: The Strava route ID.
Inputs: route_id (required).
get_segmentB
Get detailed info about a segment: distance, grade, elevation, location, star count, effort count, and your PR.
Args: segment_id: The Strava segment ID.
Inputs: segment_id (required).
get_segment_effortB
Get detailed information about a specific segment effort.
Args: effort_id: The segment effort ID.
Inputs: effort_id (required).
get_segment_effortsA
List your efforts on a specific segment. Optionally filter by date range.
Args: segment_id: The Strava segment ID. start_date_local: Optional start date (ISO 8601, e.g. 2025-01-01T00:00:00Z). end_date_local: Optional end date (ISO 8601). per_page: Items per page (default 30).
Inputs: segment_id (required), start_date_local, end_date_local, per_page. Returns: result
get_segment_effort_streamsB
Get time-series stream data for a specific segment effort.
Args: effort_id: The segment effort ID. keys: Comma-separated stream types (same as activity streams).
Inputs: effort_id (required), keys.
get_segment_streamsC
Get stream data for a segment (distance, altitude, latlng).
Args: segment_id: The Strava segment ID.
Inputs: segment_id (required).
get_starred_segmentsB
List the authenticated athlete's starred segments.
Args: page: Page number (default 1). per_page: Items per page (default 30).
Inputs: page, per_page. Returns: result
get_upload_statusA
Check the processing status of an activity upload.
Args: upload_id: The upload ID returned from a previous upload.
Inputs: upload_id (required).
monthly_summaryA
Summary of all activities from the past 30 days. Total distance, time, elevation, and calories by sport type.
Inputs: no named parameters.
star_segmentC
Star or unstar a segment.
Args: segment_id: The Strava segment ID. starred: True to star, False to unstar.
Inputs: segment_id (required), starred (required).
update_activityA
Update an existing activity. Requires activity:write scope. Only provide the fields you want to change.
Args: activity_id: The Strava activity ID to update. name: New name for the activity. sport_type: New sport type (e.g. Run, Ride, Swim). description: New description. trainer: Set True/False for trainer flag. commute: Set True/False for commute flag. gear_id: ID of gear to associate (e.g. "b12345"). Use "none" to remove.
Inputs: activity_id (required), name, sport_type, description, +3 more.
update_athlete_weightC
Update the authenticated athlete's weight.
Args: weight_kg: Athlete's weight in kilograms.
Inputs: weight_kg (required).
weekly_summaryA
Summary of all activities from the past 7 days. Total distance, time, elevation, and calories by sport type.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 37 tools
Each tool targets a distinct resource and action, with clear separation between activities, segments, routes, clubs, athlete profiles, and summaries. Even similar tools like get_recent_activities and get_activities_by_date have unambiguous differences in filtering.
Most tools follow a consistent verb_noun pattern (e.g., create_activity, get_activity, update_activity), but a few like monthly_summary and weekly_summary deviate from this pattern, using noun_adjective instead.
With 37 tools, the server is on the heavy side. While it covers a broad domain, this number exceeds the recommended range and may overwhelm agents, making selection and navigation more difficult.
The tool set covers most CRUD operations for activities, segments, routes, clubs, and athlete data, plus exports and summaries. A notable gap is the absence of a delete activity tool, but overall the surface is comprehensive.
Maintenance
Related MCP Connectors
Pace is a remote MCP server that exposes wearable and fitness data to Claude via the Model Context Protocol. It connects to Garmin, Oura, Whoop, Polar, Fitbit and 20+ devices and provides 15 tools for querying sleep, activity, recovery, and training data. Hosted on Google Cloud Run, OAuth 2.1 authentication, Streamable HTTP transport. Instructions: First you need to create an account at: https://pacetraining.co and connect your wearables. After that you can connect the remote Server via Custom Connector in Claude and OAuth 2.1 Flow startet.
Connect Claude to your Intervals.icu watch data for fitness, workout review, and plan writing.
Strava MCP tools for AI: athletes, activities, segments, clubs, routes. Powered by HAPI MCP server.
tri-train is a training platform for triathletes that syncs activities from Strava and Garmin and exposes them to Claude through a remote MCP server. Ask Claude how your last block went, why your run pace dropped, or whether you are fresh enough for Sunday's race, and it answers from your real data: activities with laps and grade-adjusted pace, weekly load and the performance management chart (CTL/ATL/TSB), sleep, HRV and resting heart rate, and your race calendar with predictions. Claude can also act: create and adjust planned workouts with structured intervals, push them to your Garmin watch, add races and write notes. Every change is journaled and can be undone. Read and write access are separate OAuth scopes, and the server enforces them on every call. Built and hosted in Switzerland by a triathlete; data stays on our own servers (Swiss revDSG / GDPR).
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables Claude to access and analyze your Strava activities through OAuth authentication. Supports retrieving activity lists and detailed workout data for fitness tracking and analysis.2-
- FlicenseAqualityDmaintenanceConnects Claude to your Strava account for analyzing training, predicting race times, and generating periodized training plans via natural language.13-
- AlicenseNot gradedqualityCmaintenanceConnects Claude to Strava data for natural language queries about rides, stats, and activities.8 npmMIT
- AlicenseAqualityDmaintenanceConnects Claude to your Strava account so you can query your activities, stats, routes, and segments using natural language.2717 npm1MIT