Strava
Read and log activities, comments, kudos and athlete stats on Strava.
About
Strava ships in the w6w first-party pack. It declares 9 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
- App id
io.w6w.strava- Version
- 0.1.2
- Author
- w6w
- Licence
- MIT
- Categories
- Productivity
Overview
Strava brings an athlete’s activity data into a workflow — reading and logging activities, comments, kudos and stats. Activity actions list an athlete’s activities, read one in detail, create a manually-logged activity, and update an existing one’s details, alongside reading the comments and kudos left on a specific activity and the effort zones it was recorded in.
Athlete actions read the connected athlete’s own profile and their aggregate stats — recent, year-to-date and all-time totals across their sport of choice. Because Strava’s access tokens are short-lived, refreshing happens automatically behind the scenes so a scheduled workflow keeps working hours or days after the original connection.
This app deliberately does not cover file-based activity uploads (a separate multipart flow), or Strava’s segments, routes, clubs and gear resources, focusing instead on the read-and-log loop around individual activities and an athlete’s own stats.
Build with Strava
Three routes to the same 9 actions. The Workflow tab is generated from Strava's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
List Athlete Activities
activity-list List the authenticated athlete's activities, most recent first.
Get Athlete Stats
athlete-stats-get Fetch recent, year-to-date and all-time totals for the authenticated athlete. The athlete ID must match the authenticated athlete's own ID.
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying Strava's real ids.
{
"manifestVersion": "2",
"name": "strava-example",
"steps": [
{
"id": "activity-comments-list",
"uses": {
"app": "io.w6w.strava",
"action": "activity-comments-list",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"activityId": "<activityId>"
}
}
]
}Here are some of the things you can do
-
List Activity Comments
readactivity-comments-list -
Create Activity
performactivity-create -
Get Activity
readactivity-get -
List Activity Kudos
readactivity-kudos-list -
List Athlete Activities
readactivity-list
+4 more actions available
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for Strava, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to Strava. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "activity-create",
payload: {
name: "<value>",
sportType: "<value>",
startDateLocal: "<value>",
elapsedTime: "<value>",
// description: "<value>",
// distance: "<value>",
// trainer: "<value>",
// commute: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value);npm install -g @w6w/cliw6w run conn_YOUR_CONNECTION_ID --action activity-create --payload '{"name":"<value>","sportType":"<value>","startDateLocal":"<value>","elapsedTime":"<value>"}'Give an AI agent Strava — without giving it Strava's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.strava#activity-comments-list",
"input": {
"activityId": "<activityId>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's Strava connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
What the agent gets
Credentials it can't read
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
A tool surface scoped to the caller
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
A durable workflow in one call
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Health-aware discovery
Strava's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. Strava itself is MIT, and the runtime that executes it is source-available (FSL).
Health checks
Strava declares its own checks, so its health is a property of the app rather than something the host guesses at.
Strava platform status
Atlassian Statuspage rollup for status.strava.com, with per-component detail. Unauthenticated and unsigned.
API rate-limit headroom
The 15-minute and daily windows off x-ratelimit-limit / x-ratelimit-usage, read from GET /athlete.