# TrainRec (remote · api.trainrec.app)

Your AI assistant logs your meals and workouts, then plans your week from what you did.

- Trust score: 80/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `api.trainrec.app`: 80/100 (this document), [markdown](https://verifymcp.io/servers/app-trainrec-trainrec/api.md), [page](https://verifymcp.io/servers/app-trainrec-trainrec/api)

## Channel facts

- Endpoint: `https://api.trainrec.app/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 97/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 5196 tokens (~152/item across 34 items; 34 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 84/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 52% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 7 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 35 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the TrainRec MCP server?

TrainRec is a hosted endpoint at https://api.trainrec.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

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

### Cursor

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

### VS Code

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

### Codex

```toml
[mcp_servers.app-trainrec-trainrec]
url = "https://api.trainrec.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "app-trainrec-trainrec": {
      "type": "remote",
      "url": "https://api.trainrec.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add app-trainrec-trainrec --url 'https://api.trainrec.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  app-trainrec-trainrec:
    url: "https://api.trainrec.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "app-trainrec-trainrec": {
      "Transport": "http",
      "Url": "https://api.trainrec.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add app-trainrec-trainrec -t streamable-http -u 'https://api.trainrec.app/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-15 (score 78, +1)

- [security] Tool “trainrec_set_reminder” rewrote its description, which is the text the model reads
- [functional] Server version: 1.0.0+7a993c95e7a8 → 1.0.0+de64a3137af9
- [cosmetic] “trainrec_set_reminder” added an optional parameter “amount”
- [cosmetic] “trainrec_set_reminder” added an optional parameter “date”

### 2026-11-14 (score 77, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-13 (score 77, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “trainrec_edit_food” rewrote its description, which is the text the model reads
- [security] Tool “trainrec_log_food” rewrote its description, which is the text the model reads
- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 1.0.0+b1ba19ea1ea5 → 1.0.0+7a993c95e7a8
- [cosmetic] “trainrec_edit_food” added an optional parameter “planned”

### 2026-11-12 (score 76)

First indexed and scored.

## MCP tools (34)

### `trainrec_overview` (~112 tokens)

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 person's latest workout. suggestedNext is the app's own pick from their rotation when nothing is planned today. Read-only.

### `trainrec_list_workouts` (~77 tokens)

List workouts

Workouts between two dates, newest first, with each exercise and how many of its sets were done. Sets themselves are not included.

Input parameters:

- `from` (string): YYYY-MM-DD, inclusive.
- `limit` (integer): Default 20, at most 100.
- `to` (string): YYYY-MM-DD, inclusive.

### `trainrec_get_workout` (~54 tokens)

Get a workout

One workout with every set, in the person's unit, and its version.

Input parameters:

- `id` (string, required)
- `unit` (string): Unit for every weight in this call. Defaults to the person's own unit.

### `trainrec_exercise_history` (~179 tokens)

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 reaches it. pace is a projection at the current rate.

Input parameters:

- `exerciseId` (string, required)
- `limit` (integer): Most recent sessions to return. Default 10.
- `target` (number): A one-rep max to reach, in unit.
- `unit` (string): Unit for every weight in this call. Defaults to the person's own unit.

### `trainrec_list_exercises` (~46 tokens)

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.

Input parameters:

- `query` (string)

### `trainrec_food_day` (~53 tokens)

Food for a 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.

Input parameters:

- `day` (string): YYYY-MM-DD. Default today.

### `trainrec_recent_changes` (~40 tokens)

Recent changes

The latest changes to this log, newest first, with who made each one and its seq number.

Input parameters:

- `limit` (integer): Default 20.

### `trainrec_plan_workout` (~276 tokens)

Plan a workout to follow

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 seconds. A workout that already happened is recorded with save_workout.

Input parameters:

- `day` (string): YYYY-MM-DD. Default today.
- `exercises` (array, required): In the order performed, by exercise id (built-in or custom).
- `fresh` (boolean): true puts a workout started by mistake back to a plan: no set done, no start time. Send the whole plan.
- `id` (string): Omit to create.
- `name` (string, required): e.g. "Easy 5K and core", "Upper body A".
- `notes` (string): Shown at the top while they follow it: the goal of the session, cues.
- `summary` (string)
- `unit` (string): Unit for every weight in this call. Defaults to the person's own unit.
- `version` (integer): Required when id is given.

### `trainrec_save_workout` (~264 tokens)

Save a 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.

Input parameters:

- `day` (string): YYYY-MM-DD. Default today.
- `exercises` (array, required): In the order performed, by exercise id (built-in or custom).
- `finishedAt` (string): When it ended, ISO with offset. Marks a logged workout finished.
- `id` (string): Omit to create.
- `name` (string, required): e.g. "Push Day".
- `notes` (string)
- `reopen` (boolean): true takes the finish off a workout ended by mistake, so it is under way again.
- `startedAt` (string): When it started, ISO with offset, if the person said ("this morning at 7"). Kept when editing.
- `summary` (string): One short line for the change list, e.g. "Logged Push Day".
- `unit` (string): Unit for every weight in this call. Defaults to the person's own unit.
- `version` (integer): Required when id is given.

### `trainrec_delete_workout` (~51 tokens)

Delete a workout

Removes one workout, given its id and version. The person can undo it in the app.

Input parameters:

- `id` (string, required)
- `summary` (string)
- `version` (integer, required)

### `trainrec_log_food` (~175 tokens)

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 numbers ("just note it"), leave perServing out: it shows as numbers not added yet, until edit_food gives it perServing. planned: true puts a meal on a day ahead (or later today) without counting it in any total until it is eaten (edit_food planned: false).

Input parameters:

- `entries` (array, required)
- `summary` (string)

### `trainrec_edit_food` (~157 tokens)

Edit a food entry

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.

Input parameters:

- `day` (string)
- `id` (string, required)
- `meal` (string)
- `name` (string)
- `perServing` (object): For ONE serving, as the label or a reliable source states it.
- `planned` (boolean): false: eaten. true: planned, not eaten yet.
- `servingLabel` (string)
- `servings` (number)
- `summary` (string)
- `version` (integer, required)

### `trainrec_delete_food` (~44 tokens)

Delete a food entry

Removes one food entry, given its id and version. The person can undo it in the app.

Input parameters:

- `id` (string, required)
- `version` (integer, required)

### `trainrec_set_targets` (~132 tokens)

Set daily 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.

Input parameters:

- `carbsG` (number, required)
- `fatG` (number, required)
- `kcal` (number, required)
- `nutrients` (object)
- `proteinG` (number, required)

### `trainrec_settings` (~97 tokens)

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 phone. Read-only.

### `trainrec_change_settings` (~281 tokens)

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; progress counts from their current trend. baseWeight: what a plate-loaded or Smith machine's sled or bar weighs empty, for one exercise (0 when not counted), or a barbell exercise's bar when it is not the standard 45 lb / 20 kg (an EZ or trap bar); it does not change sets already logged. birthYear: the year they were born, used only to estimate their maximum heart rate for heart rate zones. The change shows in the app with Undo.

Input parameters:

- `baseWeight` (object)
- `birthYear` (integer): The year they were born.
- `exerciseCalories` (string)
- `foodShows` (array)
- `goalUnit` (string): Unit of weightGoal. Defaults to the person's.
- `unit` (string)
- `weightGoal` (number): Weight to reach, in goalUnit. 0 clears the goal.

### `trainrec_save_routine` (~121 tokens)

Save a 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.

Input parameters:

- `exercises` (array, required): In the order performed, by exercise id (built-in or custom).
- `id` (string)
- `name` (string, required)
- `notes` (string)
- `summary` (string)
- `unit` (string): Unit for every weight in this call. Defaults to the person's own unit.
- `version` (integer)

### `trainrec_get_routine` (~54 tokens)

Get a routine

One routine with every set, in the person's unit, and its version.

Input parameters:

- `id` (string, required)
- `unit` (string): Unit for every weight in this call. Defaults to the person's own unit.

### `trainrec_delete_routine` (~52 tokens)

Delete a routine

Removes one routine, given its id and version. Workouts already done from it stay. The person can undo it in the app.

Input parameters:

- `id` (string, required)
- `version` (integer, required)

### `trainrec_add_exercise` (~87 tokens)

Add a custom 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).

Input parameters:

- `equipment` (string)
- `kind` (string, required)
- `muscles` (array)
- `name` (string, required)

### `trainrec_undo_change` (~48 tokens)

Undo a 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.

Input parameters:

- `seq` (integer, required)

### `trainrec_measurements` (~150 tokens)

Body measurements over time

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 value has its id and version.

Input parameters:

- `from` (string): YYYY-MM-DD.
- `kind` (string)
- `limit` (integer): Most recent days to return. Default 60, at most 400.
- `to` (string): YYYY-MM-DD.

### `trainrec_log_measurement` (~126 tokens)

Log a 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.

Input parameters:

- `at` (string): When it was taken, ISO or YYYY-MM-DD HH:MM. Default now.
- `kind` (string, required)
- `unit` (string)
- `value` (number, required)
- `value2` (number)

### `trainrec_delete_measurement` (~44 tokens)

Delete a measurement

Removes one reading, given its id and version. The person can undo it in the app.

Input parameters:

- `id` (string, required)
- `version` (integer, required)

### `trainrec_import_measurements` (~108 tokens)

Import measurement history

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.

Input parameters:

- `app` (string, required)
- `batch` (string)
- `items` (array, required)

### `trainrec_import_file` (~155 tokens)

Import a Strong or Hevy export

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.

Input parameters:

- `batch` (string): Returned by the first call; pass it on later pieces of the same file.
- `format` (string): Detected from the header when omitted.
- `text` (string, required): The CSV text, header line first.
- `unit` (string): Unit for every weight in this call. Defaults to the person's own unit.

### `trainrec_import_workouts` (~150 tokens)

Import workouts from another app

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.

Input parameters:

- `app` (string, required): Where these came from, e.g. "FitNotes", "JEFIT", "Notes app".
- `batch` (string): Returned by the first call; pass it on later calls in the same import.
- `unit` (string): Unit for every weight in this call. Defaults to the person's own unit.
- `workouts` (array, required)

### `trainrec_import_food` (~116 tokens)

Import food history from another app

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.

Input parameters:

- `app` (string, required): Where these came from, e.g. "MyFitnessPal".
- `batch` (string): Returned by the first call; pass it on later calls in the same import.
- `entries` (array, required)

### `trainrec_undo_import` (~43 tokens)

Undo an import

Removes everything one import added, given its batch id. All or nothing: refused if any of it has been edited since.

Input parameters:

- `batch` (string, required)

### `trainrec_reminders` (~39 tokens)

List 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` (~670 tokens)

Set a 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 weeks in a row, sent only if this week has no workout yet) go at a local time, and each is skipped that day once it is done. goal goes when a daily number is approaching or has reached its target (calories, a macro, or a nutrient with a target), not between 22:00 and 07:00. custom says the person's own words at a time. recap sends the day's calories and protein against their targets and its workout, at a time, every day it is on. Every reminder needs its trigger from the person: a time (their local time, 24-hour HH:MM) for timed kinds, or the amount left for an approaching goal alert. If they didn't say one, or said only "before 9 am", ask them what time; never choose it yourself. At most 20 reminders and 6 notifications a day. It shows in the app under the assistant's name, with Undo. threshold goes once, the first time today's total of a food number goes over an amount the person sets, whatever their target. check goes at a time only if today's total is still under (or over) the amount they set. Both need the whole trigger from the person: the food number, over or under, the amount, and for check a time outside 22:00 to 07:00. If they say "my target", say the number back and use that number. Set one up only when the person asks for it. A workout reminder can be for one day (date) instead of days of the week, for a planned workout: "remind me at 5 before Tuesday's workout". Its time is still the one the person says.

Input parameters:

- `amount` (object): threshold and check only.
- `at` (string): Local time, HH:MM 24-hour, as the person says it. Required for every kind but goal; ask them if they didn't say.
- `date` (string): workout only: the one day it is for, YYYY-MM-DD, instead of days.
- `days` (array): 1 = Monday to 7 = Sunday. Leave out for every day.
- `goal` (object): goal only.
- `id` (string): To change an existing reminder. Leave out to add one.
- `kind` (string, required)
- `meal` (string): log_food only.
- `on` (boolean): Default true. false keeps it but sends nothing.
- `streak` (string): streak only. training_weeks: weeks in a row with a workout; training_days: days in a row with a workout or food logged.
- `text` (string): custom only. What it says, up to 80 characters: "Take creatine".
- `version` (integer): Required with id.

### `trainrec_delete_reminder` (~59 tokens)

Delete a 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.

Input parameters:

- `id` (string, required)
- `version` (integer, required)

### `trainrec_find_issues` (~81 tokens)

Find known 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.

Input parameters:

- `query` (string, required): What went wrong or what they want, in a few words.

### `trainrec_report_issue` (~159 tokens)

Report a bug or idea

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.

Input parameters:

- `details` (string, required): What happened, where in the app, and what they expected; or, with issueId, what this person adds.
- `issueId` (integer): A matching issue from find_issues.
- `kind` (string)
- `title` (string): A new issue: one plain line, like "Rest timer does not show on the watch".

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/app-trainrec-trainrec/api#diagnostics

## Score history

- 2026-11-21: 80
- 2026-11-20: 80
- 2026-11-19: 79
- 2026-11-18: 79
- 2026-11-17: 79
- 2026-11-16: 78
- 2026-11-15: 78
- 2026-11-14: 77
- 2026-11-13: 77
- 2026-11-12: 76

## Common questions

### What is the TrainRec MCP server?

TrainRec is an MCP server listed in the public MCP registry as app.trainrec/trainrec. Your AI assistant logs your meals and workouts, then plans your week from what you did. This page covers its hosted endpoint (https://api.trainrec.app/mcp).

### Is the TrainRec MCP server safe to use?

TrainRec scores 80 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the TrainRec MCP server expose?

TrainRec exposes 34 tools: trainrec_overview, trainrec_list_workouts, trainrec_get_workout, trainrec_exercise_history, trainrec_list_exercises, and 29 more. Their descriptions and schemas cost roughly 4,300 tokens of context every time the server is loaded.

### Does the TrainRec MCP server require authentication?

Yes. TrainRec asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the TrainRec MCP server still maintained?

TrainRec is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the TrainRec MCP server?

VerifyMCP ran 13 checks on TrainRec, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://api.trainrec.app/mcp
- Website: https://trainrec.app/
- Changelog RSS feed: https://verifymcp.io/servers/app-trainrec-trainrec/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/app-trainrec-trainrec/api/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/app-trainrec-trainrec/api.json
- HTML version of this page: https://verifymcp.io/servers/app-trainrec-trainrec/api
