Skip to main content

MCP server for Strava — training load analysis, weekly plans, and activity insights

Project description

Strava MCP

An MCP server that connects Claude to your Strava data. Get training load analysis, weekly plans, and activity insights — all through conversation.

What it does

  • Recent activities — distances, times, heart rates
  • Training load analysis — ATL, CTL, TSB metrics with advice (rest or train?)
  • Weekly training plan — recommended hours and workout types based on your current form
  • Weekly statistics — volume trends over time

Quick install

1. Create a Strava API app

Go to strava.com/settings/api and create an app with:

  • Website: http://localhost
  • Authorization Callback Domain: localhost

Note your Client ID and Client Secret.

2. Run the installer

Open a terminal and paste:

curl -sSL https://raw.githubusercontent.com/ArjanLig/strava-mcp/main/install.sh | bash

This will install everything, walk you through Strava authorization, and configure Claude Desktop automatically.

3. Restart Claude Desktop

That's it! Ask Claude about your Strava activities.

Manual install

If you prefer to set things up yourself:

uvx strava-training-mcp --auth

Then add to your Claude Desktop config (Settings → Developer → Edit Config):

{
  "mcpServers": {
    "strava": {
      "command": "uvx",
      "args": ["strava-training-mcp"]
    }
  }
}

Example prompts

  • "What were my last 5 rides?"
  • "How is my training load looking?"
  • "Give me a training plan for this week"
  • "Show my weekly stats for the past 8 weeks"

Troubleshooting

"Missing credentials" error Run uvx strava-training-mcp --auth to set up authentication.

"Token expired" errors Tokens are refreshed automatically. If it persists, run uvx strava-training-mcp --auth again.

Credentials location ~/.strava-mcp/config.json

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

strava_training_mcp-0.2.1.tar.gz (10.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

strava_training_mcp-0.2.1-py3-none-any.whl (10.8 kB view details)

Uploaded Python 3

File details

Details for the file strava_training_mcp-0.2.1.tar.gz.

File metadata

  • Download URL: strava_training_mcp-0.2.1.tar.gz
  • Upload date:
  • Size: 10.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.0

File hashes

Hashes for strava_training_mcp-0.2.1.tar.gz
Algorithm Hash digest
SHA256 53b7307f787296a8367b58bdb1ee4c7e0dff9868fbbb7b23ed1702c1c542e34f
MD5 d8b69e5576ad6ccfab8ca5c9cb17dc39
BLAKE2b-256 2c1ec4fa7566997a6cd8cc15e03d043a6306d85f59c09741c5b61282d6caf9a4

See more details on using hashes here.

File details

Details for the file strava_training_mcp-0.2.1-py3-none-any.whl.

File metadata

File hashes

Hashes for strava_training_mcp-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 7eba090db56f6c0de631c76572110d3ddc4576bd8b3a1f01986e1600cdf141eb
MD5 da2144f02249886c391c54916527e4f0
BLAKE2b-256 19458704e4aca9e62a133e7dc3cadc20de447a066d401c1114d0a7511fae998d

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page