strava-mcp
MCP server that exposes Strava API v3 data (activities, segments, routes, clubs, gear, streams) as tools for any MCP client. Read-only by default, with an optional --write flag to enable mutating operations.
README
strava-mcp
MCP server for the Strava API v3. Exposes Strava data — activities, segments, routes, clubs, gear, and streams — as tools that any MCP client (Claude Desktop, Claude Code, etc.) can call.
Read-only by default. Pass --write to enable mutating tools (create/update activities, star segments).
OpenClaw-specific onboarding and sidecar setup: OPENCLAW.md.
Getting started
1. Create a Strava API application
Go to https://www.strava.com/settings/api and create an application. Note your Client ID and Client Secret.
2. Set up credentials
cp .env.example .env
Add your STRAVA_CLIENT_ID and STRAVA_CLIENT_SECRET to .env.
3. Build
pnpm install
pnpm build
4. Authenticate
pnpm auth
This opens your browser to authorize with Strava. After you approve, it automatically exchanges the code for tokens and saves STRAVA_ACCESS_TOKEN and STRAVA_REFRESH_TOKEN to your .env file. All scopes are requested (read_all, profile:read_all, activity:read_all, activity:write).
5. Test locally
pnpm inspect
Opens the MCP Inspector web UI where you can browse tools and call them interactively. Credentials are loaded from .env automatically.
You can also run the server directly:
pnpm start
6. Configure your MCP client
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"strava": {
"command": "node",
"args": ["/absolute/path/to/strava-mcp/build/index.js"],
"env": {
"STRAVA_ACCESS_TOKEN": "your-access-token"
}
}
}
}
To enable write tools (create/update activities, star segments), add "--write" to args:
{
"mcpServers": {
"strava": {
"command": "node",
"args": ["/absolute/path/to/strava-mcp/build/index.js", "--write"],
"env": {
"STRAVA_ACCESS_TOKEN": "your-access-token"
}
}
}
}
Claude Code
claude mcp add strava node /absolute/path/to/strava-mcp/build/index.js
Automatic token refresh
Strava access tokens expire. To enable automatic refresh, provide all four env vars:
{
"env": {
"STRAVA_ACCESS_TOKEN": "your-access-token",
"STRAVA_REFRESH_TOKEN": "your-refresh-token",
"STRAVA_CLIENT_ID": "your-client-id",
"STRAVA_CLIENT_SECRET": "your-client-secret"
}
}
When a request returns 401 and refresh credentials are available, the server will automatically request a new access token from Strava's OAuth endpoint and retry the request.
Environment variables
| Variable | Required | Description |
|---|---|---|
STRAVA_ACCESS_TOKEN |
Yes | Strava OAuth2 bearer token |
STRAVA_REFRESH_TOKEN |
No | Enables automatic token refresh on 401 |
STRAVA_CLIENT_ID |
No | Required alongside refresh token |
STRAVA_CLIENT_SECRET |
No | Required alongside refresh token |
Tools
Read tools (always available)
Athlete
| Tool | Description |
|---|---|
get_athlete |
Get the authenticated athlete's profile |
get_athlete_stats |
Get athlete stats (totals, recent, YTD, all-time) |
get_athlete_zones |
Get heart rate and power zones |
Activities
| Tool | Description |
|---|---|
list_activities |
List the athlete's activities (filterable by before/after timestamps) |
get_activity |
Get full details of a specific activity |
list_activity_comments |
List comments on an activity |
list_activity_kudoers |
List athletes who kudoed an activity |
list_activity_laps |
List laps of an activity |
get_activity_zones |
Get heart rate/power zones for an activity |
get_activity_streams |
Get time-series data (heartrate, power, cadence, GPS, etc.) |
Segments
| Tool | Description |
|---|---|
get_segment |
Get details of a specific segment |
explore_segments |
Find popular segments within a bounding box |
list_starred_segments |
List the athlete's starred segments |
get_segment_effort |
Get details of a segment effort |
list_segment_efforts |
List efforts on a segment, optionally filtered by date |
get_segment_streams |
Get data streams for a segment |
get_segment_effort_streams |
Get data streams for a segment effort |
Routes
| Tool | Description |
|---|---|
get_route |
Get details of a specific route |
list_athlete_routes |
List routes created by an athlete |
get_route_streams |
Get data streams for a route |
Clubs
| Tool | Description |
|---|---|
get_club |
Get details of a specific club |
list_athlete_clubs |
List the athlete's clubs |
list_club_members |
List members of a club |
list_club_activities |
List recent activities in a club |
Gear
| Tool | Description |
|---|---|
get_gear |
Get details of a piece of equipment |
Write tools (requires --write flag)
| Tool | Description |
|---|---|
create_activity |
Create a manual activity |
update_activity |
Update an existing activity (name, description, sport type, gear, etc.) |
star_segment |
Star or unstar a segment |
Documentation
- Use cases — example prompts and what you can do with the server
- Architecture — file structure, data flow, and component responsibilities
- Design decisions — rationale behind the read/write split, token refresh strategy, thin client approach, and other trade-offs
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.