Strava MCP server for AI agents

Live

OAUTH 2.0

FITNESS

Analytics

Strava gives your agent fitness data from each user's Strava account: read activities, streams, laps, and zones, track segment efforts and athlete stats, browse routes and clubs, and log manual activities.

  • Per-user credentials: each call uses the actual user's token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Strava
agent · Acme Q3
Run
How far have I run so far this year?
S
strava_get_athlete_stats
94ms
Training agent
You have run 812 km across 96 runs this year, with 9,140 m of elevation gain.
Sources: Strava athlete stats
strava
96 runs
18:29
Message Claude...

Tools your training agent reaches for on Strava, scoped per user.

CALL ANY TOOL
28 tools for fitness on Strava: read activities, laps, streams, and zones, track segments and efforts, browse routes, clubs, and gear, and create or update activities.
strava_create_activity
Create activity
Create a manual activity for the authenticated athlete. Returns the created activity with its id. Use this to log an activity by hand; it cannot attach GPS files. Requires the activity:write scope.
Parameters
Name
Type
Required
Description
elapsed_time
integer
Required
Duration of the activity in seconds. Example: 1800.
name
string
Required
Title of the activity. Example: Morning Run.
sport_type
string
Required
Sport type of the activity, using Strava's sport type names such as Run, Ride, Swim, Walk, Hike or Workout. Example: Run. One of: `AlpineSki`, `BackcountrySki`, `Badminton`, `Basketball`, `Canoeing`, `Cricket`, `Crossfit`, `Dance`, `EBikeRide`, `Elliptical`, `EMountainBikeRide`, `Golf`, `GravelRide`, `Handcycle`, `HighIntensityIntervalTraining`, `Hike`, `IceSkate`, `InlineSkate`, `Kayaking`, `Kitesurf`, `MountainBikeRide`, `NordicSki`, `Padel`, `PhysicalTherapy`, `Pickleball`, `Pilates`, `Racquetball`, `Ride`, `RockClimbing`, `RollerSki`, `Rowing`, `Run`, `Sail`, `Skateboard`, `Snowboard`, `Snowshoe`, `Soccer`, `Squash`, `StairStepper`, `StandUpPaddling`, `Surfing`, `Swim`, `TableTennis`, `Tennis`, `TrailRun`, `Velomobile`, `VirtualRide`, `VirtualRow`, `VirtualRun`, `Volleyball`, `Walk`, `WeightTraining`, `Wheelchair`, `Windsurf`, `Workout`, `Yoga`.
start_date_local
string
Required
Start time of the activity as an ISO 8601 date-time in the athlete's local time. Example: 2025-06-15T07:30:00Z.
commute
integer
Optional
Set to 1 to mark the activity as a commute. Example: 1. One of: `0`, `1`.
description
string
Optional
Free-text description of the activity. Example: Easy run along the river.
distance
number
Optional
Distance covered in meters. Example: 5000.
trainer
integer
Optional
Set to 1 to mark the activity as done on a trainer or treadmill. Example: 1. One of: `0`, `1`.
strava_explore_segments
Explore segments
strava_get_activity
Get activity
strava_get_activity_streams
Get activity streams
strava_get_activity_zones
Get activity zones
strava_get_athlete
Get athlete
strava_get_athlete_stats
Get athlete stats
strava_get_athlete_zones
Get athlete zones
strava_get_club
Get club
strava_get_gear
Get gear
strava_get_route
Get route
strava_get_route_streams
Get route streams
strava_get_segment
Get segment
strava_get_segment_effort
Get segment effort
strava_get_segment_effort_streams
Get segment effort streams
strava_get_segment_streams
Get segment streams
strava_get_upload
Upload get
strava_list_activities
List activities
strava_list_activity_comments
List activity comments
strava_list_activity_kudos
List activity kudos
strava_list_activity_laps
List activity laps
strava_list_athlete_clubs
List athlete clubs
strava_list_athlete_routes
List athlete routes
strava_list_segment_efforts
List segment efforts
strava_list_starred_segments
List starred segments
strava_star_segment
Star segment
strava_update_activity
Update activity
strava_update_athlete
Update athlete
Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Strava tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["strava"], toolNames: [
    "strava_list_activities",
    "strava_get_activity",
    "strava_get_athlete_stats"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Summarize my training load for the last 4 weeks" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["strava"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Summarize my training load for the last 4 weeks" }],
  tools,
});

// Execute the tool call with the user's vaulted Strava OAuth token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["strava"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Summarize my training load for the last 4 weeks" }],
  tools,
});

// Tool call runs with the user's vaulted Strava OAuth token
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["strava"] }, pageSize: 100,
});

const agent = new Agent({
  name: "training_agent",
  model: "gemini-2.5-pro",
  instruction: "Strava tools scoped to this user",
  tools,
});

await agent.run("Summarize my training load for the last 4 weeks");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Strava tool. Click to copy, paste into your agent, done.
Activities
Copy the prompt
Copied
List my last 10 activities.
Copy the prompt
Copied
Show heart rate and pace streams for my Sunday long run.
Copy the prompt
Copied
Log a 45 minute manual yoga session for today.
Segments
Copy the prompt
Copied
Find popular cycling segments around Golden Gate Park.
Copy the prompt
Copied
Show my efforts on the Hawk Hill segment.
Copy the prompt
Copied
Star the Hawk Hill segment.
Athlete and routes
Copy the prompt
Copied
What are my year-to-date ride totals?
Copy the prompt
Copied
List the routes I have created.
Copy the prompt
Copied
List the clubs I belong to.
SEE HOW AUTH WORKS
Each user signs in to Strava once, and Scalekit stores and refreshes their tokens. Credentials stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
Strava
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Strava
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Strava
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Strava
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other analytics and media connectors.
Support and Ops Teams
Meeting prep
Pulls agenda, participant context, and open action items before every meeting.
Test other agents
See the same per-user auth pattern across other analytics and media connectors.
OPS
Meeting prep agent
Assemble the agenda, HubSpot attendee history, and open action items from Gmail before every meeting on the calendar.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared Strava token looks fine in a demo. In production every activity the agent logs looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Strava today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Strava as the user or through a shared service account?
As the user. Each user signs in to Strava once, and Scalekit stores and refreshes their tokens. Activities the agent creates or updates are attributed to that user in your audit trail, not a shared service account.
Where is the Strava OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in Strava?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example the read tools without strava_create_activity or strava_update_activity, which change the athlete's activity feed. Scalekit also enforces scope checks before every API call.
What happens when a user revokes Strava access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
What can the agent change in Strava?
Only a few things. strava_create_activity logs a manual activity, strava_update_activity edits an activity the athlete owns, strava_star_segment stars or unstars a segment, and strava_update_athlete changes the athlete's weight. Every other tool reads data.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""strava"": {
""url"": ""https://mcp.scalekit.com/strava"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.strava]
url = ""https://mcp.scalekit.com/strava""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""strava"": {
""url"": ""https://mcp.scalekit.com/strava"",
""type"": ""http""
}
}
}