"How to implement intent recognition in MCP" matching MCP servers:

An AI recipe recommendation server based on the MCP protocol, providing functions such as recipe query, classification filtering, intelligent dietary planning, and daily menu recommendation.

Enables AI assistants to convert raw and cooked weights for meat and poultry by cut and cooking method from USDA data, calculate how much raw meat to buy for cooked servings, and look up cooking yields and sample ranges.

Enables AI assistants to plan and track McDonald's visits by locating stores, estimating commute calories, recommending nutrition-targeted menu combinations, monitoring orders, running spaced-repetition vocabulary practice during waits, and recording progress in a local dashboard.

Enables AI agents to rank US healthcare organizations for clinical trial site feasibility, predicting patient accrual for a Graves' disease protocol using claims and registry data.

Enables voice-driven family check-ins and safety escalation through five MCP tools over Streamable HTTP, recording check-ins, scheduling recurring reminders with grace windows, detecting missed check-ins, raising critical help alerts, and resolving them from a live dashboard. All reads and writes flow through these tools into a SQLite store, with safety rules ensuring explicit help requests override upbeat wording and never duplicate or downgrade alerts.

MyChart MCP Server

Enables ChatGPT and compatible AI clients to query read-only Garmin Connect data—including sleep, HRV, heart rate, Body Battery, wellness metrics, and activities—through a hosted OAuth-backed MCP connection using a personal API key.

Enables users to describe workouts in plain English and have them created as structured Garmin Connect workouts with pace, HR, power, cadence targets, and repeat blocks. Also provides full workout lifecycle management including listing, updating, deleting, and scheduling to the calendar.

Provides local MCP tools to query your own Xiaomi Mi Fitness health data (sleep, workouts, heart rate, etc.) stored in a local SQLite database, enabling AI assistants to access personal health records without exposing credentials.

MCP server that lets you ask questions about your Garmin training history in plain language. It ingests FIT files into DuckDB locally and exposes typed tools for analyzing activities, streams, and summaries.

Ask your Oura Ring about sleep, readiness, activity, stress and heart rate in ChatGPT or Claude, in any language. Read-only, 10 task-oriented tools; runs in a sandbox demo mode with no credentials.

Enables Claude Desktop to query and analyze diabetes data from Omnipod 5 and Glooko through natural language, providing clinical audit and triage insights such as time in range, trends, and bolus analysis.

An MCP server that lets Claude plan cycling training in intervals.icu, upload workouts to the calendar, and review planned versus actual outcomes, fitness trends, and power curves.

Enables AI agents to look up businesses, find free appointment slots, book, list and cancel appointments at salons, barbershops, nail and brow studios and clinics. Works read-only without a customer login by returning a pre-filled booking link, and can also run against a built-in demo with sample businesses.

Solar vitamin D: whether the sun where you are can make vitamin D right now, how many minutes your Fitzpatrick skin type needs for a target dose, which months of the year synthesis is possible at your latitude, and how much a sun session produced. Computed from solar geometry, a clear-sky UV model with ozone and altitude, and live Open-Meteo UV data.

Enables an agent to fetch one night of Eight Sleep data as ready-made text — scores, sleep stages, HRV, heart and respiratory rate versus your averages, and bed/room temperatures — plus short summaries of earlier nights for a morning check-in. Read-only, so nothing on the mattress can be changed.

Provides Claude Code and Claude Desktop with safe, read-only access to your local Garmin training data, readiness decisions, run details, and trends so you can get coaching advice in natural language.

This MCP server enables an AI to look up Brazilian food composition data — searching foods by Portuguese name, retrieving exact per-100 g or gram-scaled nutrient values, summing nutrients across a meal, and comparing up to 10 foods side by side — rather than estimating numbers. It preserves missing and trace values explicitly and cites TACO 4ª ed. in every response.

Enables assistants and agents to look up sourced nutrition, glycemic load, and micronutrient data for Indian dishes and ingredients by amount in grams or household measures, including meal totals, nutrient rankings, and estimated daily targets.

Runs entirely locally to provide calm, animated breathing sessions that open in a browser or as an artifact, with tools for matched or custom sessions, pattern listings, and a breathing-break prompt, while collecting no data.

Enables AI assistants to query a user's own Garmin Connect training, health, and recovery history through Garmin's official Personal API, backed by a local cache and built-in analysis tools.

Connects AI assistants to SmartGym on Mac, enabling users to review workouts, tweak routines, and build training programs in plain English, with changes syncing to iPhone and Apple Watch.

SuperGlookoQuery is a Claude Desktop extension (MCPB) that connects to Glooko diabetes device data and exposes it as clinical analysis tools (time in range, GMI, trends, enriched bolus/basal analysis, charting), for any pump/CGM combination Glooko supports rather than one fixed device. It's a fork of Richard Hall's podquery-mcp, reworked to discover each account's own data shape rather than assumi

Provides read-only access to a therapy practice's client portal, letting users view upcoming appointments, paperwork requests, standing forms, balances, receipts and secure message threads, and download completed documents and payment receipts as PDFs. It authenticates either with server-side credentials or by relaying requests through the user's already signed-in browser tab, and never sends messages, signs forms, uploads files, or makes payments.

Enables AI assistants to read your SisRUN training plan with your own credentials and answer questions about prescribed workouts, like weekly coach plans, in a structured format.

Enables querying of current A\&E waiting times, specialist outpatient waiting times, and general outpatient clinic quotas in Hong Kong using natural language through MCP.

Provides local, read-only MCP access to Google Health API v4, enabling users to query recorded workouts, heart-rate samples, and related health data through natural language in an MCP client.

Enables AI agents to read and analyze Dexcom CGM data through tools for current glucose, recent historical readings, and glucose statistics such as time in range.

Enables MCP-capable AI apps to query a user's own Garmin sleep, HRV, stress, Body Battery, heart-rate, activity, and body-metric data through Garmin's official Personal API in a read-only, locally run setup.

Enables AI agents to query Matrix / Johnson Fitness ride history, exposing per-10-second power, cadence, resistance and heart-rate samples plus cross-ride views like power curves, training volume, and ride comparisons. Runs over a cached history downloaded without credentials, or signs in once to refresh it.