# TrainRec

> TrainRec is a freemium MCP server for health and science. Your AI assistant plans workouts and logs meals in a free training and food app. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** iOS, Android, API
- **Website:** https://trainrec.app
- **MCP Registry name:** app.trainrec/trainrec
- **Categories:** health and science, productivity
- **Listing updated:** 2026-11-14

## About

TrainRec flips the usual logging flow: you describe a routine, a run or a calorie target to your assistant, and the plan appears in the app. During a workout the app steps you through each set with rest timers on phone or watch, and records what you actually did rather than what was planned. Afterwards the assistant reads the real log and adjusts what comes next, and each change shows who made it.

Food is logged from a sentence such as a burrito described with what you left uneaten, with calories, protein, carbs and sodium filled in. The app also tracks water, weight, waist, body fat and blood pressure, shows a 30-day weight trend, and syncs both ways with Apple Health. An in-app AI called Coach can estimate a meal from a photo or read a nutrition label; it is described as an AI, not a human coach, and gives no medical advice.

It connects to Claude, ChatGPT, Grok and other assistants that support custom MCP connectors.

## Features

- **Assistant-built plans:** Ask for a routine, run or week and it lands in the app.
- **Guided workouts:** Step-by-step sets with rest timers on phone, Apple Watch or Garmin.
- **Sentence food logging:** Describe a meal and macros are filled in without searching a food list.
- **Body measurements:** Track weight, waist, body fat, blood pressure and water.
- **Review and adjust:** The assistant reads your real log and updates the next sessions.
- **Apple Health sync:** Data syncs both ways.

## Good for

- Plan a home strength routine three days a week
- Log breakfast by telling your assistant what you ate
- Ask why the same workout felt harder this time
- Make Saturday's run easier after a tough session
- Watch the weight trend against a goal

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http trainrec https://api.trainrec.app/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://api.trainrec.app/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "trainrec": {
      "url": "https://api.trainrec.app/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "trainrec": {
      "type": "http",
      "url": "https://api.trainrec.app/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "trainrec": {
      "serverUrl": "https://api.trainrec.app/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "trainrec": {
      "type": "http",
      "url": "https://api.trainrec.app/mcp"
    }
  }
}
```

## Tools

- `trainrec_overview`: Today's date and weight unit for this person, today's food against their targets, their last few workouts, their routines, notes they left, and what they changed in the app since the assistant's last change (sets done differently from a plan show the planned values beside them). Each planned workout says whether it is reviewed: the app shows "Reviewed by" if the assistant wrote the plan after the 
- `trainrec_list_workouts`: Workouts between two dates, newest first, with each exercise and how many of its sets were done. Sets themselves are not included.
- `trainrec_get_workout`: One workout with every set, in the person's unit, and its version.
- `trainrec_exercise_history`: One exercise over time: personal records (heaviest, best estimated one-rep max, most reps, best session volume) and every session that included it, oldest first. Warm-ups and sets not done are excluded. pace is a straight line through the last 12 weeks of session estimated one-rep maxes (from weights and reps only), with where that line is in 4, 8 and 12 weeks; with target, also the day the line r
- `trainrec_list_exercises`: Exercise ids, names and kinds, built-in and custom, optionally filtered by words in the name. The kind decides which set fields apply.
- `trainrec_food_day`: Everything eaten on one day, each entry with its id and version, totals by meal and for the day, and what is left of the targets.
- `trainrec_recent_changes`: The latest changes to this log, newest first, with who made each one and its seq number.
- `trainrec_plan_workout`: Plans a workout for the person to do: saves it in TrainRec, where their phone and watch walk them through it one set at a time, with each set's target (weight and reps, time or distance) and the rest after it. Every set starts as not yet done. Given an id and version, it changes an existing plan, even during the workout: sets already done are kept, and the phone and watch show the change within se
- `trainrec_save_workout`: Logs a new workout, or replaces an existing one given its id and version: the whole workout as it should now be, so anything left out is removed. Sets default to done; planned sets for a later day have done: false. The change shows in the person's app with Undo.
- `trainrec_delete_workout`: Removes one workout, given its id and version. The person can undo it in the app.
- `trainrec_log_food`: Adds one or more food entries, each with its numbers PER SERVING and the number of servings. perServing takes the macros and any label nutrient (sodiumMg, potassiumMg and the rest); a nutrient left out counts as unknown, not zero. A glass of plain water is an entry named "Water" with kcal and macros 0 and waterMl. Each entry is its own change, with Undo. When the person asks to note a food without
- `trainrec_edit_food`: Changes fields of one food entry, given its id and version. Fields left out stay as they are; perServing is replaced whole. planned: false marks a planned food eaten, with servings or perServing in the same call as what was actually had.
- `trainrec_delete_food`: Removes one food entry, given its id and version. The person can undo it in the app.
- `trainrec_set_targets`: Sets the daily calorie and macro targets, and optionally a target for any other nutrient (the keys in overview.foodNutrients): a ceiling for the ones to limit, such as sodiumMg, cholesterolMg, sugarG, saturatedFatG or caffeineMg, and an amount to reach for the rest, such as potassiumMg, fiberG or calciumMg. nutrients left out keeps the ones already set; {} clears them.
- `trainrec_settings`: The person's settings: weight unit, which nutrients beyond the macros show on their Food and Today screens, how much of a day's workout calories is added to their calorie target, their weight goal, and what the sled or bar of a plate-loaded or Smith machine weighs empty (baseWeights; a set's weight is the total, so plates loaded = weight - base). Also lists what only the person can change on the p
- `trainrec_change_settings`: Changes settings. unit: lb or kg. foodShows: the full list of extra nutrients shown, in order, replacing the old one ([] shows only the macros). exerciseCalories: none, half or all of each day's bonus calories (active calories beyond a usual day, or workout calories when there is no daily count) added to the calorie target. weightGoal: a body weight in goalUnit (or theirs), or 0 to clear it; progr
- `trainrec_save_routine`: Creates a routine (a reusable workout plan the person starts from the app), or replaces one given its id and version. Same shape as a workout, without a day.
- `trainrec_get_routine`: One routine with every set, in the person's unit, and its version.
- `trainrec_delete_routine`: Removes one routine, given its id and version. Workouts already done from it stay. The person can undo it in the app.
- `trainrec_add_exercise`: Makes a custom exercise with a name, kind and muscles. equipment: "plate" for a plate-loaded machine or "smith" for a Smith machine gives it a sled or bar its base weight is counted from (change_settings baseWeight).
- `trainrec_undo_change`: Puts a record back the way it was before one change, given the change's seq. Refused if the record has been changed again since.
- `trainrec_measurements`: Body measurements over time, one kind at a time, one value per day (the last reading of the day), in the person's units, newest last: weight, body fat, tape measurements, calories eaten per day, resting heart rate, HRV, blood pressure and sleep, and from Oura readiness, sleep score, temperature change and minutes stressed and restored. Without kind, the latest reading of every kind recorded. Each 
- `trainrec_log_measurement`: Records one measurement: weight, body fat, a tape measurement, blood pressure, resting heart rate, HRV or sleep, in the unit given (lb, kg, %, in, cm, bpm, ms, mmHg, min). Blood pressure takes systolic as value and diastolic as value2.
- `trainrec_delete_measurement`: Removes one reading, given its id and version. The person can undo it in the app.
- `trainrec_import_measurements`: Imports past measurements (weight, body fat, tape, blood pressure, resting heart rate, HRV, sleep, daily calories), each with its time as the source wrote it, kind, value and unit, and origin when the source names one. Up to 1000 per call; the same batch id on later calls makes one import. Readings already recorded are skipped.
- `trainrec_import_file`: Imports a CSV exported from Strong (workouts or measurements) or Hevy, as text exactly as the file has it; the server parses it. A large file can be sent in pieces split on whole workouts, each with the header line and the same batch id. Strong exports omit their unit. Workouts already imported are skipped. Only Strong and Hevy formats.
- `trainrec_import_workouts`: Imports past workouts from another app or file. Exercises are matched to existing ones by name; unmatched names become custom exercises, listed in the result. Up to 100 workouts per call; the same batch id on later calls makes one import, undone together. Workouts already imported from the same app are skipped.
- `trainrec_import_food`: Imports past meals from another nutrition app or file: each entry's day, meal, name, numbers PER SERVING and servings. Up to 200 entries per call; the same batch id on later calls makes one import, undone together. Entries already imported from the same app are skipped.
- `trainrec_undo_import`: Removes everything one import added, given its batch id. All or nothing: refused if any of it has been edited since.
- `trainrec_reminders`: The person's reminders (notifications on their phone): what each says, when, whether it is on, and who set it up. Read-only.
- `trainrec_set_reminder`: Reminders are TrainRec's notifications on the person's phone. They start at zero: none exist until the person asks their assistant (you) to set one up, so when they ask to be reminded of something, this is how. Adds a reminder, or changes one (give its id and version). Kinds: weigh_in, log_food (optionally one meal), workout (names today's planned workout if there is one) and streak (training week
- `trainrec_delete_reminder`: Removes one reminder, given its id and version. To stop it for a while instead, set_reminder with on false. The person can undo it in the app.
- `trainrec_find_issues`: Bugs and ideas already sent to the TrainRec team that look like what the person describes, best match first, with whether each is fixed. Call this before report_issue: if one matches, add to it rather than sending a new one. Read-only.
- `trainrec_report_issue`: Send a bug or an idea to the TrainRec team, only after the person agrees to. Call find_issues first: if an issue matches, pass its issueId with what this person adds; otherwise pass kind, title and details for a new one. Say what happened and where in the app, never anything about their health beyond what the bug needs.

## FAQ

### Is the log free?

The site describes a free workout and food log with no limits; Connect and Coach are separate tiers whose prices are not shown.

### Where does it run?

On iPhone and Android, with Apple Watch and Garmin support.

### Which assistants work?

Claude, ChatGPT, Grok and any assistant that supports custom MCP connectors.

### Is Coach a human trainer?

No. It is an AI and does not give medical advice.

### Is TrainRec free?

TrainRec has a free plan, with paid plans for more usage or features.

### How do I add TrainRec to Claude Code?

Run this command in your terminal: claude mcp add --transport http trainrec https://api.trainrec.app/mcp

### What are the best alternatives to TrainRec?

The closest alternatives to TrainRec are Ha MCP, Tooluniverse, Concord MCP, Oya Browser and note1.

## Alternatives

- [Ha MCP](https://ai-powered.com/mcp/ha-mcp): Ha MCP is an open-source MCP server for productivity.
- [Tooluniverse](https://ai-powered.com/mcp/tooluniverse): Tooluniverse is an open-source MCP server for health and science.
- [Concord MCP](https://ai-powered.com/mcp/concord-mcp): Concord MCP is a freemium MCP server for developer tools.
- [Oya Browser](https://ai-powered.com/mcp/oya-browser): Oya Browser is a freemium MCP server for browser automation.
- [note1](https://ai-powered.com/mcp/note1): note1 is an MCP server for productivity.
- [Later Stages](https://ai-powered.com/mcp/later-stages): Later Stages is a free MCP server for health and science.
- [CalderFlow](https://ai-powered.com/mcp/calderflow): CalderFlow is a free MCP server for design and media.
- [MedXpert 标准检索连接器](https://ai-powered.com/mcp/medxpert-2): MedXpert 标准检索连接器 is a free MCP server for legal and government.

---
Source: https://ai-powered.com/mcp/trainrec
