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

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 (no https://, 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

1. Fork this repo to your GitHub account

2. In the Cloudflare dashboard, go to Workers & Pages → Add → Continue with GitHub

3. Authorize Cloudflare to access your GitHub account

4. Select your forked strava-mcp repo 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 wrangler commands must be run from inside the project directory (where wrangler.toml lives). If you get a "missing worker name" error, cd into 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

1. Go to Claude.ai → Settings → Integrations

2. Add a new remote MCP server:

   https://strava-mcp.YOUR_SUBDOMAIN.workers.dev/mcp

3. 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 main deploys automatically)

• Free tier: Cloudflare Workers free tier supports 100k requests/day