Strava MCP Server
Connects Claude to Strava data for natural language queries about rides, stats, and activities.
README
Strava MCP Server — Cloudflare Workers
A personal Model Context Protocol server for Strava, hosted on Cloudflare Workers (free tier). Connect Claude to your Strava data for natural language queries about your rides, stats, and activities.
Tools
| Tool | Description |
|---|---|
get_athlete |
Your Strava profile |
get_stats |
Recent, YTD, and all-time ride totals |
get_activities |
List recent activities with power, HR, elevation |
get_activity |
Detailed view of a specific activity |
create_activity |
Log a manual activity (strength training, etc.) |
update_activity |
Rename or update an existing activity |
All distances returned in miles, elevation in feet.
Setup
1. Create a Cloudflare Account
Go to cloudflare.com and sign up for a free account if you don't have one.
2. Create a Strava API App
Follow the Strava API Getting Started guide to create your API application. When setting up the app use these values:
- Website:
https://strava-mcp.YOUR_SUBDOMAIN.workers.dev - Authorization Callback Domain:
strava-mcp.YOUR_SUBDOMAIN.workers.dev(nohttps://, no path)
Note your Client ID and Client Secret — you will need them in step 6.
Your Cloudflare subdomain is shown at dash.cloudflare.com → Workers & Pages.
3. Fork and Connect to Cloudflare
- Fork this repo to your GitHub account
- In the Cloudflare dashboard, go to Workers & Pages → Add → Continue with GitHub
- Authorize Cloudflare to access your GitHub account
- Select your forked
strava-mcprepo and click Next, then Deploy
This connects your GitHub repo to Cloudflare — every push to main will automatically redeploy the worker.
4. Install Wrangler
Wrangler is Cloudflare's CLI tool. You'll need Node.js v18+ installed first.
npm install -g wrangler
wrangler login
Important: All
wranglercommands must be run from inside the project directory (wherewrangler.tomllives). If you get a "missing worker name" error,cdinto the project folder first.
5. Create KV Namespace
Cloudflare KV is used to store your Strava OAuth tokens.
wrangler kv namespace create TOKENS
Copy the output id into wrangler.toml:
[[kv_namespaces]]
binding = "TOKENS"
id = "PASTE_YOUR_ID_HERE"
6. Set Secrets
Store all sensitive values in Cloudflare's secret store rather than in wrangler.toml. This keeps them out of version control and safe to commit publicly.
wrangler secret put STRAVA_CLIENT_SECRET --name strava-mcp
# Paste your Strava Client Secret when prompted
wrangler secret put STRAVA_CLIENT_ID --name strava-mcp
# Paste your Strava Client ID when prompted
wrangler secret put WORKER_URL --name strava-mcp
# Paste your full worker URL, e.g. https://strava-mcp.YOUR_SUBDOMAIN.workers.dev
7. Deploy
npm install
npm run deploy
8. Connect Strava (one-time OAuth)
Visit your worker URL in a browser to authorize Strava:
https://strava-mcp.YOUR_SUBDOMAIN.workers.dev/auth/login
Authorize the app on Strava. Tokens are stored in Cloudflare KV and auto-refreshed on every request.
You can verify everything is working by visiting the status page:
https://strava-mcp.YOUR_SUBDOMAIN.workers.dev/status
Add to Claude.ai
- Go to Claude.ai → Settings → Integrations
- Add a new remote MCP server:
https://strava-mcp.YOUR_SUBDOMAIN.workers.dev/mcp - That's it — Claude can now query your Strava data naturally
Example prompts:
- "How many miles have I ridden this year?"
- "Show me my last 5 activities"
- "What were my power numbers on my ride Saturday?"
- "Log a 45-minute strength training session for this morning"
Local Development
Create a .dev.vars file (gitignored) for local secrets:
STRAVA_CLIENT_SECRET=your_secret_here
STRAVA_CLIENT_ID=your_client_id_here
WORKER_URL=http://localhost:8787
Then run:
npm run dev
Architecture
Claude.ai → POST /mcp → Cloudflare Worker → Strava API
↕
Cloudflare KV
(OAuth token storage)
- Transport: MCP Streamable HTTP (spec version 2025-03-26)
- Auth: Strava OAuth 2.0 with automatic token refresh
- Storage: Cloudflare KV (single-user, personal server)
- Auto-deploy: Cloudflare Workers + GitHub integration (push to
maindeploys automatically) - Free tier: Cloudflare Workers free tier supports 100k requests/day
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.