"Understanding local computer vision models like YOLO" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Hosted Apple Health MCP for Claude and ChatGPT, works outside the US. iPhone app, no local server.
PushPress MCP server for ChatGPT, Claude and any AI agent: list members, book class reservation, check in member, cancel reservation and update membership plan in your own PushPress account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to PushPress yourself; Cotlet does not store your password and you need no PushPress API key. About the official PushPress API: PushPress has a Platform API and an SDK that doubles as a local MCP server, both using an API key from Settings > Security & Access, but they are mostly read-only beyond creating customers and invitations (checked 11 Oct 2026). Booking, check-ins, plan changes and class cancellations are done by staff in Core. Setup and FAQ: https://cotlet.dev/integrations/pushpress-api-mcp-server
Marathon physiology MCP server — 12 tools for race prediction, pacing strategy, fueling plans, running economy, caffeine protocols, heat acclimation, and Strava-connected training load. Citation-backed models from peer-reviewed exercise physiology literature.
Free nutrition and fitness tools for AI assistants. It helps you track calories, macros, goals, workouts, body measurements, and barcode-scanned foods, then lets your AI use that real context to answer questions like what you ate today, how much protein you are missing, what dinner fits your remaining calories, or how your weight is changing.