MCP: Strava Segment & Club Intel

MCP server wrapping strava-segment-intel for AI agents. Four tools over the public Strava segment/club surface the locked-down API no longer hands out - logged-out, public-only, and PII-minimized.

Responsible use. Logged-out PUBLIC Strava data only. No login, no athlete credentials, no individual-athlete identities, leaderboards, routes, or activities. Club output is aggregate (member count only). For segment/route and area analytics, not individual tracking.

Tools

Tool	Args	Returns
get_segments	segment_ids, include_derived_metrics, limit	Public segments with name, sport, location, and distance / grade / elevation / climb category derived from the public geometry stream.
get_club	club_ids, limit	Aggregate club info - name, sport, location, type, member count. No member identities.
area_rollup	segment_ids, limit	Popular-segments-by-area rollups (region x activity): counts, distance/grade/elevation stats, hardest climb.
explore_segments	bounds or center_lat/lng + radius_km, activity_type, limit	Best-effort bounding-box discovery. Strava's explore endpoint is auth-gated logged-out, so this fail-softs with a note unless the upstream actor has a warm browser session.

Modes

• list_tools - emit the tool catalog (free, no charge). Includes the x402/Skyfire payment descriptor.
• call_tool - { "mode": "call_tool", "tool": "get_segments", "args": { "segment_ids": ["229781"] } }
• batch - up to 10 {tool, args} calls in one run.

{ "mode": "call_tool", "tool": "area_rollup", "args": { "segment_ids": ["229781", "8109834"] } }

Connect it to an MCP client

This Actor is exposed as a remote MCP tool through Apify's hosted MCP server. Point any MCP-compatible client (Claude Desktop, Cursor, VS Code, or an OpenAI / LangChain / LlamaIndex agent) at Apify's server with this Actor enabled:

{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com?tools=seibs.co/mcp-strava-segment-intel",
      "headers": { "Authorization": "Bearer <YOUR_APIFY_TOKEN>" }
    }
  }
}

Get a token (free) from Apify Console -> Settings -> API & Integrations. The Actor then appears as a callable tool. Run mode=list_tools first (free) to fetch every tool's live JSON schema, then call one:

{ "mode": "call_tool", "tool": "get_segments", "args": { } }

Prefer a direct call? Hit the Actor straight through the Apify API / SDK - no MCP client required:

from apify_client import ApifyClient
client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("seibs.co/mcp-strava-segment-intel").call(run_input={
    "mode": "call_tool", "tool": "get_segments", "args": {},
})
items = client.dataset(run["defaultDatasetId"]).list_items().items

Pricing

Flat $0.005 per MCP tool call. The upstream strava-segment-intel actor charges its own segment_record ($0.006), metric_enrichment ($0.012), and area_rollup ($0.015) events directly to the same run (pass-through).

Agentic payments

x402 (USDC on Base) and Skyfire ready - an AI agent can pay per tool call with no pre-provisioned token when the operator enables MCP monetization. Calls through Apify bill via standard PPE. See the payments block in the list_tools output.

Who it's for

AI agents (Claude, Cursor, OpenAI, LangChain) doing cycling/running route, segment, and area research - and the fitness-app builders, coaches, and analytics tools shut out by Strava's Nov-2024 API lockdown.