Strava MCP Server — 35 AI Tools | Claude, ChatGPT & More

Strava MCP ServerStrava MCP server with 35 ready-to-use AI tools. Connect Strava to Claude, ChatGPT, Gemini, or any MCP-compatible AI assistant. Cloud MCP connector — no install, no Docker, works from any browser.Category: Health & Fitness. 35 tools available. Authentication: OAuth.Your AI-powered athletic performance analystWhy Strava + AI?Strava has all your training data, but getting meaningful insights means clicking through dozens of activities one by one. Stop manually comparing runs and rides when AI can analyze your entire season in seconds.Example prompts you can send your AI about Strava

Ask: "Compare my running pace this month vs last month"
AI does: AI pulls your recent activities, calculates average pace trends, and highlights improvements or areas where you slowed down.

Ask: "What are my top 5 longest rides this year?"
AI does: AI searches your activity history, ranks rides by distance, and shows elevation gain, average speed, and time for each.

Ask: "Show my segment times on Mountain Loop Trail"
AI does: AI fetches your segment efforts, compares them over time, and shows how close you are to your PR.

Ask: "Summarize my training load for this week"
AI does: AI aggregates all activities, calculates total distance, elevation, and time, and compares against your weekly averages.

Featured Strava Tools

get-activities: Get a paginated list of activities for the authenticated athlete, ordered newest to oldest. Returns activity ID, name, sport type, distance (meters), moving time (seconds), elevation gain, start date, and summary stats. This is the PRIMARY tool for finding activity IDs needed by most other activity tools. WHEN TO USE: User asks "show my recent activities", "what did I do last week?", "list my runs", "how far did I ride yesterday?", or any question about recent/past activities. FILTERING BY DATE: Use "before" and "after" params with Unix timestamps (seconds since epoch). EXAMPLE: "Activities this week" -> after=1707955200 (Monday midnight UTC as Unix timestamp). EXAMPLE: "Last 5 activities" -> perPage=5 (no date filter needed, already sorted newest first). PAGINATION: Default 30 per page, max 200. Use page=2 for older activities. CRITICAL: Distance is in METERS (divide by 1000 for km, by 1609.34 for miles). Moving time is in SECONDS (divide by 60 for minutes, by 3600 for hours).

get-athlete-stats: Get lifetime and recent activity statistics for a specific athlete. Returns totals and recent (last 4 weeks) stats for running, riding, and swimming: distance, moving time, elevation gain, and activity count. Also returns the biggest ride/run distance and longest ride/run. WHEN TO USE: User asks "what are my stats?", "how far have I run this year?", "total cycling distance?", "how many runs have I done?", "what is my biggest ride?", or any lifetime/recent summary question. CRITICAL: Requires athleteId. Call get-authenticated-athlete FIRST to get the athlete ID. STEP-BY-STEP: 1) get-authenticated-athlete -> extract id. 2) get-athlete-stats with that id. EXAMPLE: athleteId=12345678 (get this from get-authenticated-athlete, NOT a made-up number).

get-segment-efforts: Get all the authenticated athlete's efforts (attempts) on a specific segment. Returns effort ID, elapsed time, moving time, start date, distance, average speed, average HR, and the activity it belongs to. An "effort" is one attempt at riding/running a segment during an activity. WHEN TO USE: User asks "how many times have I done this segment?", "my times on Hawk Hill", "PR history for this segment", "am I getting faster on this climb?", or "all my attempts". STEP-BY-STEP for "am I improving on segment X?": 1) Call get-segment-efforts with the segment ID. 2) Compare elapsed_time across efforts sorted by date. Filter by date range with startDateLocal/endDateLocal (ISO 8601) to narrow results. CRITICAL: This requires a SEGMENT ID (the road section), NOT an effort ID. Get segment IDs from explore-segments, get-starred-segments, or get-activity (segment_efforts field).

get-activity-streams: Get detailed time-series data for an activity including GPS, heart rate, power, cadence, etc.

explore-segments: Search for popular Strava segments within a geographic bounding box. Returns a list of segments with name, distance, average grade, climb category, and start/end coordinates. Up to 10 results. WHEN TO USE: User asks "find segments near me", "popular running segments in Central Park", "cycling climbs near San Francisco", "segments in this area", or "find hills to ride near [city]". CRITICAL: Requires a bounding box with SW and NE corners (latitude/longitude). STEP-BY-STEP for "segments near [city]": 1) Look up approximate lat/lng for the city. 2) Create a bounding box ~5-10 km around it (add/subtract ~0.05 degrees). 3) Call explore-segments with the box coordinates. EXAMPLE: Segments in San Francisco -> swLat=37.7, swLng=-122.5, neLat=37.82, neLng=-122.35. Use activityType="running" or "riding" to filter. Climb categories: 0=uncategorized, 1=Cat 4 (easiest), 5=HC (hardest).

get-activity-zones: Get time-in-zone distribution for a specific activity. Returns how many seconds were spent in each heart rate zone and power zone (if applicable). WHEN TO USE: User asks "how much time in zone 2?", "heart rate zone breakdown for my run", "was I in the aerobic zone?", "zone distribution", or "training intensity analysis". STEP-BY-STEP: 1) Call get-activities to find the activity ID. 2) Call get-activity-zones with that ID. For zone boundary definitions, use get-athlete-zones (returns the athlete's zone settings). NOTE: Only available for activities with heart rate data (HR monitor) or power data (power meter).

Frequently Asked Questions about StravaHow do I connect Strava to Claude or ChatGPT?Create a free LearnToSpeak.ai account, add your Strava credentials in the dashboard, and paste the generated OAuth URL into Claude.ai's custom connectors or ChatGPT's developer apps. The integration runs fully in the cloud — no desktop app, no CLI, no local install.Does it cost anything to connect Strava?The Strava integration is free during the LearnToSpeak.ai public beta. You only need a paid plan from Anthropic or OpenAI (Claude Pro/Max/Team or ChatGPT Plus/Pro/Team) since custom connectors require it on the AI provider side.Which AI assistants support the Strava connector?Claude.ai (Pro, Max, Team, Enterprise) and ChatGPT (Plus, Pro, Team) both support the Strava integration via the MCP (Model Context Protocol) standard. The same credentials work across both platforms — add the connector once, use it everywhere.How many Strava tools does my AI get access to?Your AI gets 35 ready-to-use tools for Strava, covering the most common read and write operations. Each tool is a discrete action the AI can call on demand — no multi-step prompting, no screen scraping, no workarounds.Is it safe to give an AI access to my Strava account?Yes. Your Strava credentials are encrypted at rest with AES-256-GCM and only decrypted in memory when the AI makes a request. LearnToSpeak.ai uses OAuth 2.1 with mandatory PKCE for the AI-to-platform connection, and you can revoke access instantly from the dashboard. We never store or log the actual tool responses returned to the AI.Why use LearnToSpeak.ai instead of running an MCP server locally?Cloud MCP servers work from any browser on any device — no Node.js install, no Docker, no local ports, no maintenance. Configure Strava once in the dashboard and your AI connects from claude.ai or chat.openai.com directly. That's the entire value proposition: web AI assistants don't read your filesystem, they read our servers.What is the Strava MCP server?The Strava MCP server is a cloud-hosted integration that gives AI assistants direct access to Strava through 35 tools via the Model Context Protocol (MCP) standard. It works with Claude, ChatGPT, Gemini, and any MCP-compatible AI — no local installation or Docker required.How do I connect Strava to Claude via MCP?Sign up at LearnToSpeak.ai, add your Strava credentials, and copy the generated MCP URL into Claude.ai's custom connectors (Settings → Developer → Custom Connectors). The cloud MCP server handles the connection — no CLI, no local server, no Docker.How do I connect Strava to ChatGPT via MCP?Sign up at LearnToSpeak.ai, add your Strava credentials, and copy the generated MCP URL into ChatGPT's developer apps (Settings → Apps → Advanced → Developer mode). Works with any ChatGPT Plus, Pro, or Team account.What can AI do with Strava through MCP?Strava offers 35 MCP tools covering Track running, cycling, hiking activities and compete with friends. Ask your AI to perform any of these actions in natural language — it calls the right tool automatically.What is MCP (Model Context Protocol)?MCP is an open standard that lets AI assistants like Claude, ChatGPT, and Gemini connect directly to external apps and services. LearnToSpeak.ai hosts cloud MCP servers so you don't need to install anything locally — your AI connects from any browser.Related MCP Servers

HEVY MCP Server — 17 tools

MyFitnessPal MCP Server — 14 tools

Browse all 34 MCP servers