# How to integrate Strava MCP with Antigravity ```json { "title": "How to integrate Strava MCP with Antigravity", "toolkit": "Strava", "toolkit_slug": "strava", "framework": "Antigravity", "framework_slug": "antigravity", "url": "https://composio.dev/toolkits/strava/framework/antigravity", "markdown_url": "https://composio.dev/toolkits/strava/framework/antigravity.md", "updated_at": "2026-05-12T10:27:18.875Z" } ``` ## Introduction ### How to integrate Strava MCP with Antigravity Antigravity IDE is Google's agentic IDE, built on a VS Code-style editor and powered by models like Gemini 3.5 Flash, Gemini 3.1 Pro, Opus 4.6, and more. It treats the AI agent as a first-class teammate, planning, coding, and validating work through an Agent Manager dashboard with deep browser connectivity. In this guide, I will explain the easiest and most secure way to connect your Strava account to Antigravity IDE via Composio Connect, so it can get your latest cycling activity stats, list all runs I logged this week, show your longest ride from last month, and more without ever putting your account credentials at risk. ## Also integrate Strava with - [ChatGPT](https://composio.dev/toolkits/strava/framework/chatgpt) - [OpenAI Agents SDK](https://composio.dev/toolkits/strava/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/strava/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/strava/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/strava/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/strava/framework/codex) - [Cursor](https://composio.dev/toolkits/strava/framework/cursor) - [VS Code](https://composio.dev/toolkits/strava/framework/vscode) - [OpenCode](https://composio.dev/toolkits/strava/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/strava/framework/openclaw) - [Hermes](https://composio.dev/toolkits/strava/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/strava/framework/cli) - [Google ADK](https://composio.dev/toolkits/strava/framework/google-adk) - [LangChain](https://composio.dev/toolkits/strava/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/strava/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/strava/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/strava/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/strava/framework/crew-ai) ## TL;DR ### Why use Composio? Composio provides: - Access to 1,000+ managed apps from a single MCP endpoint. This makes it convenient for agents to run cross-app workflows. - Programmatic tool calling. Allows LLMs to write code in a remote workbench to handle complex tool chaining. Reduces to-and-fro with LLMs for frequent tool calling. - Large tool response handling outside the LLM context. This minimizes context bloat from large tool responses. - Dynamic just-in-time access to thousands of tools across hundreds of apps. Composio loads the tools your agent needs, so LLMs are not overwhelmed by tools they do not need. ## Connect Strava to Antigravity ### Connect Strava to Antigravity Antigravity does not ship with one-click custom MCP install links yet, so configuration goes through the IDE's raw config file. The process takes under a minute. ### 1. Open the MCP Config Go to Antigravity Settings, open the Customizations tab, then click Open MCP Config to open mcp_config.json in the editor. ### 2. Get your API key Go to the [Composio Dashboard](https://dashboard.composio.dev/~/org/connect/clients/) and copy your API key. ### 3. Add Composio to mcp_config.json Paste the following configuration into the file: ```bash { "mcpServers": { "remote-composio": { "serverUrl": "https://connect.composio.dev/mcp", "headers": { "x-consumer-api-key": "your-composio-api-key" } } } } ``` ## What is the Strava MCP server, and what's possible with it? The Strava MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Strava account. It provides structured and secure access to your fitness data, so your agent can perform actions like fetching activities, analyzing stats, logging workouts, managing routes, and exploring your social fitness feed on your behalf. - Workout tracking and retrieval: Let your agent pull detailed records of your recent runs, rides, and other logged activities, complete with stats, maps, and performance data. - Fitness analytics and progress insights: Have your agent analyze your weekly or monthly trends, highlight PRs, and summarize progress toward your training goals. - Route exploration and management: Ask your agent to list, suggest, or organize your favorite routes and segments for upcoming workouts or challenges. - Social engagement automation: Enable your agent to fetch kudos, summarize comments, or surface activity highlights from friends and clubs in your Strava network. - Activity creation and editing: Allow your agent to log new activities, edit workout details, or update activity metadata for accurate record keeping. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `STRAVA_CREATE_AN_ACTIVITY` | Create an Activity | Creates a manual activity for an athlete. Requires activity:write scope. This endpoint is for manually entered activities only. To upload activity files (FIT, TCX, GPX), use the Upload Activity endpoint instead. Required parameters: name, sport_type, start_date_local, elapsed_time. Optional parameters: type (deprecated), description, distance, trainer, commute. | | `STRAVA_EXPLORE_SEGMENTS` | Explore segments | Explore segments within a geographic bounding box. Returns the top 10 segments matching the specified geographic boundary and optional filters. Segments are sections of roads or trails where Strava athletes can compete for times. The response includes segment details like: - id: Unique segment identifier - name: Segment name - climb_category: Climbing difficulty (0=NC/flat to 5=HC/hardest) - avg_grade: Average gradient percentage - distance: Segment length in meters - elev_difference: Elevation gain in meters - start_latlng/end_latlng: Start and end coordinates - elevation_profile: URL to elevation profile image | | `STRAVA_EXPORT_ROUTE_GPX` | Export Route as GPX | Exports a Strava route as a GPX (GPS Exchange Format) file. GPX files can be used to import routes into GPS devices, other fitness apps, or mapping software. Requires read_all scope for private routes. | | `STRAVA_EXPORT_ROUTE_TCX` | Export Route as TCX | Exports a Strava route as a TCX (Training Center XML) file. TCX format is widely supported by GPS devices, fitness watches, and training software like Garmin Connect and TrainingPeaks. The exported file contains the route's waypoints, distance, and elevation profile. Requires read_all scope for private routes. | | `STRAVA_GET_ACTIVITY` | Get Activity | Retrieves detailed information about a specific activity by its ID. Returns a DetailedActivity object containing comprehensive data including distance, time, elevation, speed, heart rate, power data (if available), segment efforts, laps, splits, and more. Permissions required: - activity:read scope for activities with visibility set to 'everyone' or 'followers_only' - activity:read_all scope for activities with visibility set to 'only_me' The activity must be owned by the authenticated athlete. | | `STRAVA_GET_ACTIVITY_STREAMS` | Get activity streams | Retrieves time-series stream data for a specific activity. Streams are the raw spatial and sensor data recorded during an activity, including GPS coordinates, speed, heart rate, power, etc. Each stream type returns an array of values that correspond to specific time points during the activity. All requested streams have the same number of data points, aligned by index. Common use cases: - GPS track visualization: request 'latlng', 'altitude', 'time' - Performance analysis: request 'heartrate', 'cadence', 'watts', 'time' - Pace/speed analysis: request 'velocity_smooth', 'distance', 'time' Requires activity:read scope. Requires activity:read_all scope for Only Me (private) activities. | | `STRAVA_GET_ACTIVITY_ZONES` | Get Activity Zones | Returns the heart rate and power zones of a given activity. This is a Summit/Premium feature that provides zone distribution data showing time spent in each training zone. The response includes an array of ActivityZone objects, typically containing: - Heart rate zones: Time distribution across heart rate training zones - Power zones: Time distribution across power training zones (for cycling with power meter) Requirements: - Strava Summit/Premium subscription for the athlete who owns the activity - activity:read scope for Everyone and Followers visibility activities - activity:read_all scope for Only Me (private) activities Common errors: - 404: Activity not found or not accessible - 403: Insufficient permissions to view activity - 402: Summit subscription required | | `STRAVA_GET_ATHLETE_STATS` | Get athlete stats | Returns the activity stats of an athlete, including ride, run, and swim totals for recent (last 4 weeks), year-to-date, and all-time periods. Only includes data from activities set to 'Everyone' visibility. Use get_authenticated_athlete to obtain the required athlete ID. | | `STRAVA_GET_AUTHENTICATED_ATHLETE` | Get authenticated athlete | Retrieves the profile of the currently authenticated Strava athlete. Returns athlete information including name, location, account status, profile photos, and social connections. The level of detail depends on the OAuth scope: - With 'profile:read_all' scope: Returns detailed representation (resource_state=3) including follower counts, measurement preferences, FTP, weight, and equipment. - Without 'profile:read_all' scope: Returns summary representation (resource_state=2) with basic profile information only. This is a read-only endpoint that requires no input parameters. | | `STRAVA_GET_CLUB` | Get Club | Retrieves detailed information about a specific Strava club by its ID. Returns comprehensive club details including name, description, location (city/state/country), member count, sport type, activity types, club type (casual, racing team, company, etc.), privacy settings, and the authenticated athlete's membership status. Use STRAVA_LIST_ATHLETE_CLUBS to get club IDs for clubs the authenticated athlete belongs to, or use a known club ID from a Strava club URL. Returns a 404 error if the club does not exist. | | `STRAVA_GET_EQUIPMENT` | Get equipment | Retrieves detailed information about a specific piece of gear/equipment. Returns comprehensive details about bikes or shoes including name, brand, model, total distance, and status (primary/retired). The requesting athlete must own the gear - you cannot view other athletes' equipment. Use Cases: - Get detailed specs and usage statistics for a specific bike or shoe - Check if gear is retired or still in active use - View total distance traveled with specific equipment - Retrieve brand and model information for gear inventory Prerequisites: - Gear ID can be obtained from: 1. Get Authenticated Athlete (bikes/shoes arrays in detailed response) 2. Get Activity (gear_id field shows equipment used for that activity) Note: Gear IDs use prefixes: 'b' for bikes (e.g., 'b12345678'), 'g' for shoes (e.g., 'g12345678'). | | `STRAVA_GET_ROUTE` | Get route | Retrieve detailed information about a specific Strava route. A route is a planned path that athletes can follow, created via the Strava Route Builder. This endpoint returns comprehensive route data including: - Basic info: name, description, activity type (Ride/Run), sub_type - Geographic data: distance (meters), elevation_gain (meters), start/end coordinates - Map data: polyline for rendering the route path, map_urls - Metadata: created_at, updated_at, estimated_moving_time, private status - Segments: list of segments included in the route - Waypoints: custom waypoints added to the route Note: Requires read_all scope to retrieve private routes. | | `STRAVA_GET_ROUTE_STREAMS` | Get route streams | Get detailed stream data for a route. Returns raw GPS coordinates, elevation, and distance data points along a route's path. This data can be used for mapping, elevation profiles, and route analysis. Available stream types for routes: - latlng: Latitude/longitude coordinate pairs for mapping the route - distance: Cumulative distance along the route in meters - altitude: Elevation values in meters for elevation profiles Note: Requires read_all scope for private routes. Use list_athlete_routes to find route IDs for the authenticated athlete. | | `STRAVA_GET_SEGMENT` | Get segment | Retrieve detailed information about a specific Strava segment. A segment is a portion of a road or trail where athletes can compete for times. This endpoint returns comprehensive segment data including: - Basic info: name, activity_type (Ride/Run), city, state, country - Geographic data: distance, average_grade, maximum_grade, elevation_high/low, start/end coordinates - Map data: polyline for rendering the segment path - Statistics: effort_count, athlete_count, star_count - Records: xoms (KOM/QOM times), local_legend info - Athlete-specific stats: personal records (requires read_all scope) Note: read_all scope is required to retrieve athlete-specific segment information or to access private segments. | | `STRAVA_GET_SEGMENT_EFFORT` | Get segment effort | Retrieves detailed information about a specific segment effort by its unique ID. A segment effort represents an athlete's attempt at a particular segment during an activity. This endpoint returns performance metrics including elapsed time, distance, speed, heart rate, power, and cadence data. The segment effort ID can be obtained from: - Activity details (when using include_all_efforts=True with get_activity) - The list_segment_efforts endpoint for a specific segment Note: Requires an active Strava subscription for the authenticated athlete. | | `STRAVA_GET_SEGMENT_EFFORT_STREAMS` | Get segment effort streams | Returns stream data for a segment effort completed by the authenticated athlete. Streams provide the raw time-series data associated with a segment effort, such as GPS coordinates, altitude, speed, heart rate, power, etc. All streams for a given segment effort have the same length, with values at each index corresponding to the same point in time. Requires read_all scope. The segment effort must be from an activity owned by the authenticated athlete. Use get_activity with include_all_efforts=true or list_segment_efforts to find segment effort IDs. | | `STRAVA_GET_SEGMENT_STREAMS` | Get segment streams | Get detailed stream data for a segment. Returns raw GPS, elevation, and distance data points along a segment's route. This data can be used for mapping, elevation profiles, and route analysis. Available stream types: - distance: Distance along the segment in meters - latlng: Latitude/longitude coordinate pairs for mapping - altitude: Elevation values in meters for elevation profiles Note: Only distance, altitude, and latlng stream types are available for segments. Other stream types (like heartrate, watts) are only available for activities. Requires read_all scope for private segments. | | `STRAVA_GET_UPLOAD` | Get Upload Status | Retrieves the status of an upload by its ID. Use this endpoint to poll the processing status of an uploaded activity file. Uploads are processed asynchronously, so you should poll this endpoint (recommended: no more than once per second) until the activity_id is populated or an error is returned. Requires activity:write scope. | | `STRAVA_GET_ZONES` | Get zones | Retrieves the authenticated athlete's heart rate and power zones. This endpoint returns the athlete's configured training zones for both heart rate and power, including zone thresholds and time spent in each zone. Note: Requires the 'profile:read_all' OAuth scope. If you receive a 401 Unauthorized error, ensure your connection has this scope. | | `STRAVA_LIST_ACTIVITY_COMMENTS` | List activity comments | Retrieves comments on a specific Strava activity, sorted oldest first. Returns comment details including the comment text, author information, and timestamps. Supports cursor-based pagination for activities with many comments. Requires OAuth scope: activity:read for Everyone/Followers activities, activity:read_all for Only Me (private) activities. Note: Returns an empty list if the activity has no comments or if you don't have permission to view the activity. | | `STRAVA_LIST_ACTIVITY_KUDOERS` | List activity kudoers | Returns the athletes who kudoed an activity identified by an identifier. Requires activity:read for Everyone and Followers activities. Requires activity:read_all for Only Me activities. | | `STRAVA_LIST_ACTIVITY_LAPS` | List activity laps | Retrieves lap data for a specific Strava activity. Laps represent segments of an activity, typically auto-generated during activities like running or cycling based on distance intervals, manual lap button presses, or course segments. Each lap contains detailed metrics including timing, distance, speed, cadence, and power data. Note: Pace zones in lap data are only populated for running activities and are based on the athlete's configured race times. Authorization: - Requires 'activity:read' scope for public (Everyone) and Followers-only activities. - Requires 'activity:read_all' scope for private (Only Me) activities. | | `STRAVA_LIST_ATHLETE_ACTIVITIES` | List athlete activities | Retrieves a paginated list of activities for the authenticated athlete. Returns activity summaries including name, type, distance, duration, elevation gain, speed, heart rate data, and timestamps. Use 'before' and 'after' parameters to filter activities by date range, and 'page'/'per_page' for pagination. Requires OAuth scope: activity:read for public/followers activities, activity:read_all for private activities. Note: Returns an empty list if no activities match the criteria. | | `STRAVA_LIST_ATHLETE_CLUBS` | List athlete clubs | Retrieves a paginated list of Strava clubs the authenticated athlete is a member of. Returns club details including id, name, location, member count, sport type, and profile images. Use the club id from the response to fetch detailed club information with other club endpoints. Note: Returns an empty list if the athlete is not a member of any clubs. | | `STRAVA_LIST_ATHLETE_ROUTES` | List athlete routes | Lists routes created by a specific athlete. Returns an array of Route summaries including id, name, distance, elevation gain, and type. Private routes are filtered out unless the token has read_all scope. Only the authenticated athlete's routes can be accessed; attempting to list another athlete's routes returns 403 Forbidden. | | `STRAVA_LIST_CLUB_ACTIVITIES` | List club activities | Retrieve recent activities from members of a specific club. IMPORTANT: The authenticated athlete must be a member of the requested club to access this endpoint. Use 'List Athlete Clubs' first to get club IDs the athlete belongs to. Pagination is supported (max 200 activities total). Enhanced Privacy Mode is respected for all activities. Note: Club activities have limited data for privacy - they do not include activity IDs, dates, or full athlete names. | | `STRAVA_LIST_CLUB_ADMINISTRATORS` | List club administrators | Returns a list of the administrators of a given Strava club. The response includes each administrator's first name, last name (possibly abbreviated), and resource state. For public clubs, this endpoint is accessible without membership. For private clubs, the authenticated user may need to be a member to view administrators. Returns an empty list if the club has no visible administrators or access is restricted. | | `STRAVA_LIST_CLUB_MEMBERS` | List club members | Returns a list of the athletes who are members of a given club. The authenticated athlete must belong to the requested club to access this endpoint. Results are paginated and can be controlled using page and per_page parameters. Note: Due to privacy settings, some member information may be limited. | | `STRAVA_LIST_SEGMENT_EFFORTS` | List segment efforts | List the authenticated athlete's efforts on a given segment. Returns all segment efforts for the authenticated athlete on the specified segment, optionally filtered by date range. Segment efforts represent each time an athlete has ridden/run a particular segment. The response includes details like: - id: Unique effort identifier - elapsed_time: Time to complete the segment in seconds - moving_time: Moving time on the segment in seconds - start_date: When the effort started - distance: Distance covered in meters - average_watts: Average power output (if power data available) - average_heartrate: Average heart rate (if HR data available) - pr_rank: Personal record ranking (1=PR, 2=2nd best, 3=3rd best, null otherwise) - kom_rank: King/Queen of Mountain ranking position (if in top 10) Note: This endpoint only returns efforts for segments the authenticated athlete has actually completed. If the athlete hasn't ridden/run a segment, an empty list will be returned. | | `STRAVA_LIST_STARRED_SEGMENTS` | List starred segments | Returns a list of the authenticated athlete's starred segments with summary details including segment name, distance, elevation, grade, and location. Private segments are filtered out unless requested by a token with read_all scope. Use pagination parameters (page, per_page) to navigate through large result sets. | | `STRAVA_STAR_SEGMENT` | Star segment | Stars/Unstars the given segment for the authenticated athlete. Requires profile:write scope. | | `STRAVA_UPDATE_ATHLETE` | Update Athlete | Update the currently authenticated athlete's profile. Currently only supports updating the athlete's weight. Requires profile:write scope. | | `STRAVA_UPLOAD_ACTIVITY` | Upload Activity | Uploads a new activity file (FIT, TCX, or GPX) to create an activity on Strava. The upload is processed asynchronously. This endpoint returns an upload ID immediately, which can be used with the Get Upload endpoint to check processing status and retrieve the created activity ID once processing completes. Typical processing time is under 2 seconds. Files must be 25MB or smaller and contain actual workout data with timestamps for each trackpoint. Requires the activity:write OAuth scope. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK Once connected, Antigravity can access the Strava MCP server via Composio to run actions that you authorize directly from the agent panel. ## Complete Code None listed. ## Conclusion ### Conclusion You have successfully connected Strava to Antigravity using Composio Connect. Your agent can now use Strava securely without exposing credentials in prompts or local scripts. ## How to build Strava MCP Agent with another framework - [ChatGPT](https://composio.dev/toolkits/strava/framework/chatgpt) - [OpenAI Agents SDK](https://composio.dev/toolkits/strava/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/strava/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/strava/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/strava/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/strava/framework/codex) - [Cursor](https://composio.dev/toolkits/strava/framework/cursor) - [VS Code](https://composio.dev/toolkits/strava/framework/vscode) - [OpenCode](https://composio.dev/toolkits/strava/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/strava/framework/openclaw) - [Hermes](https://composio.dev/toolkits/strava/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/strava/framework/cli) - [Google ADK](https://composio.dev/toolkits/strava/framework/google-adk) - [LangChain](https://composio.dev/toolkits/strava/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/strava/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/strava/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/strava/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/strava/framework/crew-ai) ## Related Toolkits - [Twitter](https://composio.dev/toolkits/twitter) - Twitter is a social media platform for sharing real-time updates, conversations, and news. Stay connected, informed, and engaged with communities worldwide. - [Instagram](https://composio.dev/toolkits/instagram) - Instagram is a social platform for sharing photos, videos, and stories with your audience. It helps brands and creators engage, grow, and analyze their online presence. - [Ayrshare](https://composio.dev/toolkits/ayrshare) - Ayrshare is a Social Media API for managing, automating, and analyzing posts across multiple platforms. It helps you streamline social media workflows and centralize analytics. - [Dotsimple](https://composio.dev/toolkits/dotsimple) - Dotsimple is a social media management platform for planning, creating, and publishing content. It helps teams boost their reach with AI-powered content generation and actionable analytics. - [Tiktok](https://composio.dev/toolkits/tiktok) - Tiktok is a short-form video platform for creating, sharing, and discovering viral content. It helps creators and brands reach massive audiences with creative tools and global social features. - [Gmail](https://composio.dev/toolkits/gmail) - Gmail is Google's email service with powerful spam protection, search, and G Suite integration. It keeps your inbox organized and makes communication fast and reliable. - [Google Calendar](https://composio.dev/toolkits/googlecalendar) - Google Calendar is a time management service for scheduling meetings, events, and reminders. It streamlines personal and team organization with integrated notifications and sharing options. - [Google Drive](https://composio.dev/toolkits/googledrive) - Google Drive is a cloud storage platform for uploading, sharing, and collaborating on files. It's perfect for keeping your documents accessible and organized across devices. - [Outlook](https://composio.dev/toolkits/outlook) - Outlook is Microsoft's email and calendaring platform for unified communications and scheduling. It helps users stay organized with powerful email, contacts, and calendar management. - [Google Sheets](https://composio.dev/toolkits/googlesheets) - Google Sheets is a cloud-based spreadsheet tool for real-time collaboration and data analysis. It lets teams work together from anywhere, updating information instantly. - [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure. - [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed. - [Notion](https://composio.dev/toolkits/notion) - Notion is a collaborative workspace for notes, docs, wikis, and tasks. It streamlines team knowledge, project tracking, and workflow customization in one place. - [Slack](https://composio.dev/toolkits/slack) - Slack is a channel-based messaging platform for teams and organizations. It helps people collaborate in real time, share files, and connect all their tools in one place. - [Airtable](https://composio.dev/toolkits/airtable) - Airtable combines the flexibility of spreadsheets with the power of a database for easy project and data management. Teams use Airtable to organize, track, and collaborate with custom views and automations. - [Google Docs](https://composio.dev/toolkits/googledocs) - Google Docs is a cloud-based word processor that enables document creation and real-time collaboration. Its seamless sharing and version history make team editing and content management a breeze. - [Google Super](https://composio.dev/toolkits/googlesuper) - Google Super is an all-in-one suite combining Gmail, Drive, Calendar, Sheets, Analytics, and more. It gives you a unified platform to manage your digital life, boosting productivity and organization. - [Hubspot](https://composio.dev/toolkits/hubspot) - HubSpot is an all-in-one marketing, sales, and customer service platform. It lets teams nurture leads, automate outreach, and track every customer interaction in one place. - [Codeinterpreter](https://composio.dev/toolkits/codeinterpreter) - Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms. - [Gong](https://composio.dev/toolkits/gong) - Gong is a platform for video meetings, call recording, and team collaboration. It helps teams capture conversations, analyze calls, and turn insights into action. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Strava MCP? With a standalone Strava MCP server, the agents and LLMs can only access a fixed set of Strava tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Strava and many other apps based on the task at hand, all through a single MCP endpoint. ### Can I use Tool Router MCP with Antigravity? Yes, you can. Antigravity fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Strava tools. ### Can I manage the permissions and scopes for Strava while using Tool Router? Yes, absolutely. You can configure which Strava scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do. ### How safe is my data with Composio Tool Router? All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Strava data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)