Skip to main content
Glama
Trainzilla MCP

Trainzilla MCP

Official

tzilla-mcp (MVP, local only)

A local MCP server that lets an MCP client (Claude Desktop, Claude Code, Cursor, …) act as a Trainzilla coach. It wraps the existing GraphQL API at api.tzilla.live — no direct DB access — so all auth and business rules stay enforced by the backend.

Status: Local MVP — read tools, offline calculators, and confirm-gated write tools, plus a resource + a prompt. Not deployed anywhere. Runs entirely on your machine against your own coach login.

What it can do today (422 tools, 1 resource, 1 prompt)

Read (live data):

  • whoami, list_clients, get_client_profile

  • list_client_habits, get_habit_compliance, recent_habit_activity, master_habits

  • list_workout_plans, list_diet_plans

  • list_checkins, list_sessions, list_subscriptions, billing_summary

Calculators (offline, no network):

  • calc_tdee — BMR / TDEE / recommended calories

  • calc_macros — macro split by strategy (Standard 40/30/30, Pro g/kg, Keto)

  • calc_1rm — 1-rep-max (Epley) + %1RM weight suggestions

Write (confirm-gated): every write tool returns a preview unless called with confirm: true, so nothing changes by accident:

  • create_habit, create_master_habit, assign_master_habit

  • create_checkin (with questions), schedule_session

  • create_workout_plan, create_diet_plan

Switching from another platform (Nov 2026): bulk_invite_clients (up to 200 clients with name, phone and a private note that lands in the coach's client notes when they connect), the switch_to_trainzilla prompt, and the format-agnostic skill in skills/switch-to-trainzilla/ (a coach hands Claude any export, PDFs or a spreadsheet; Claude maps it, previews, then sends). No vendor presets: nothing here assumes a competitor's export layout.

Coverage added Oct 2026 (src/tools/*, each tool backed by one GraphQL operation and checked against the backend schema with scripts/validate-docs.mjs):

  • Client tracking — diet/workout logs, daily metrics, personal bests, exercise history, progress, health reports, intake forms, no-app (managed) clients + private portal links, contact details; coach-side logging.

  • AI coaching — review queue (approve/reject/requeue), trigger/offer, engagement, per-client preferences, AI-plans and self-cancel switches.

  • Check-ins & inbox — respond, logs, recurring schedules, clear overdue; notifications; chat room list.

  • Business — plans (create/prices/listing/active/session rules/delete), pause/cancel membership, desk payments, direct-pay claim confirm/reject, payments, invoices + settings, share links, Coach Pro pricing/checkout link, referral program, gym seat billing.

  • Community, gym, workflows, catalog, profile — community posts/comments, gym kiosks/face/check-ins/standing bookings/imports/staff/domain, workflow edit/delete + gym-wide workflows, PDF plan import, food/recipe/exercise catalog, branding/custom domain/global payout/localization, Google Calendar status, video calls.

  • Insights, catalog and promos, Nov 2026 (src/tools/insights-catalog-promos.ts) — get_client_roster (segments: needs programming / inactive / new / plan ending / on track), list_clients_with_declining_recovery, get_habit_adherence_all_clients, get_client_workout_streak, list_ai_run_history, list_client_subscriptions, get_session, get_community_unread_count; exercise catalog browse (list_exercise_body_parts, list_exercise_equipment, browse_exercise_catalog, delete_custom_exercise); discount codes (list_coupons, create_coupon, set_coupon_active); workout-days challenges (list_challenges, get_challenge_leaderboard, create_challenge, set_challenge_active, delete_challenge); reusable workout sections (list_workout_section_templates, create_/update_/delete_workout_section_template).

  • Client groups (Coach Pro / gym), Nov 2026 — list_client_groups, get_client_group, list_groups_for_client, create/update/delete group, add_group_members/remove_group_members, get_group_overview, list_group_assignments, and the fan-outs assign_workout_to_groups, assign_diet_to_groups, assign_habit_to_groups, message_groups, schedule_checkin_for_groups, book_session_for_groups, undo_group_assignment. The fan-outs preview server-side without confirm (who would get it, who is skipped and why) and are idempotent for 10 minutes. scripts/mcp-groups-e2e.mjs drives them against a local backend (TZ_API_URL=http://127.0.0.1:4100/graphql).

Validate documents against the backend schema after changing a tool:

npm run build
SCHEMA=/path/to/tzilla-be/schema.graphql GRAPHQL_PKG=/path/to/node_modules/graphql node scripts/validate-docs.mjs

Also included: upload_file (local path on stdio, or base64) → S3 key for the tools that take one (health reports, PDF plan import, member photo, receipts, community media, branding images); API-key create/list/revoke (secret shown once); Stripe/Razorpay connect (secrets masked in previews); start_google_calendar_connect (returns the sign-in URL for the coach to open).

Chat: get_client_chat_messages reads a client's DM history (needs the clientChatMessages backend query, tzilla-be#493).

Not available: taking or refunding a payment — the backend has no coach-facing refund operation, and client checkout is completed by the client's own payment.

Resource: tzilla://client/{clientId}/profile — a client's profile as JSON.

Prompt: weekly_client_review — pulls profile/habits/compliance/sessions and writes a read-only weekly review.

Related MCP server: fitness-mcp

Setup

npm install
npm run build

Create .env (see .env.example) with a coach's tokens. Easiest source — log in to the coach web app, then in the browser console:

localStorage.getItem("token")        // -> TZ_ACCESS_TOKEN
localStorage.getItem("refreshToken") // -> TZ_REFRESH_TOKEN

The server auto-refreshes the access token via refreshAccessToken when it expires.

Run

Local (stdio) — for Claude Desktop etc.:

  • Dev: npm run dev

  • Built: npm start

  • Smoke: node scripts/smoke.mjs

Remote (Streamable HTTP) — localhost only, multi-coach:

  • Dev: npm run http · Built: npm run start:http

  • Listens on http://127.0.0.1:8787/mcp (set MCP_HTTP_PORT / MCP_HTTP_HOST).

  • Smoke: node scripts/smoke-http.mjs

Auth modes

  • stdio: uses TZ_ACCESS_TOKEN (+ TZ_REFRESH_TOKEN) from env; auto-refreshes.

  • Endpoint selection:

    • TZ_API_URL wins when set.

    • Otherwise TZ_ENVIRONMENT=staging uses https://qa-be2.tzilla.live/graphql.

    • All other cases default to https://api.tzilla.live/graphql.

  • HTTP: pass-through — each request must send the coach's API key (Authorization: Bearer tz_... or x-api-key). The server never stores tokens; it forwards the caller's key to the GraphQL API, so the backend enforces scope (multi-coach safe). API keys are minted by the backend feature below.

Backend: trainer API keys (built in tzilla-be, local — not deployed yet)

  • createApiKey(name) → returns the plaintext tz_… key once + info

  • apiKeys (list, no secret) · revokeApiKey(id)

  • Auth middleware accepts tz_ keys (header x-api-key or Bearer), resolves the owning coach, and stamps lastUsedAt. Only a SHA-256 hash is stored.

Use from Claude Desktop

Add to claude_desktop_config.json (Settings → Developer → Edit Config):

{
  "mcpServers": {
    "tzilla-coach": {
      "command": "node",
      "args": ["C:/New folder/tzilla-mcp/dist/index.js"],
      "env": {
        "TZ_API_URL": "https://api.tzilla.live/graphql",
        "TZ_ACCESS_TOKEN": "<paste>",
        "TZ_REFRESH_TOKEN": "<paste>"
      }
    }
  }
}

Restart Claude Desktop, then try: "Use tzilla-coach: who am I, and list my clients."

Roadmap

  • Write tools (habits, check-ins, sessions, plans) — confirm-gated

  • Resource (client profile) + prompt (weekly review)

  • Wider read coverage (plans, check-ins, sessions, billing)

  • Backend trainer API keys / PAT (built in tzilla-be, local — needs PR + deploy)

  • Remote Streamable-HTTP transport (localhost, API-key pass-through auth)

  • Deploy the backend API-key feature; host the HTTP server (TLS) for real remote use

  • Full MCP OAuth 2.1 (replace pass-through) for a public connector

  • More resources (plans / check-in history) + prompts (e.g. "draft a plan")

Layout

src/
  config.ts   # env + tiny .env loader
  client.ts   # GraphQL client: bearer auth + refresh-on-401 + role header
  calc.ts     # offline coach math (ported from HealthMath/WorkoutMath)
  index.ts    # MCP server + tool definitions (stdio)
scripts/
  smoke.mjs   # spawns the server and lists tools (handshake check)

Available Tools

23 tools
assign_master_habitAInspect

Assign a Master Habit to one or more clients — creates a habit per client (confirm-gated).

Inputs: masterHabitId (required), clientIds (required), confirm.

billing_summaryA
Read-only
Inspect

Summarise the coach's payments: total captured amount (minor units), currency, and counts by status.

Inputs: no named parameters.

calc_1rmA
Read-only
Inspect

Estimate a 1-rep max (Epley) and %1RM weight suggestions from a working set.

Inputs: weightKg (required), reps (required).

calc_macrosA
Read-only
Inspect

Compute a macro split (protein/carbs/fat in grams) for a strategy. STANDARD=40/30/30, PRO=g/kg multipliers, KETO=25/5/70.

Inputs: calories (required), weightKg (required), strategy, proteinPerKg, +1 more.

calc_tdeeB
Read-only
Inspect

Compute BMR, TDEE, and recommended daily calories from client stats.

Inputs: gender (required), weightKg (required), heightCm (required), age (required), +3 more.

create_checkinBInspect

Schedule a check-in for a client with optional questions (confirm-gated). scheduledFor: ISO date. question.type: TEXT|NUMBER|SCALE|PHOTO.

Inputs: clientId (required), scheduledFor (required), questions, confirm.

create_diet_planBInspect

Create a diet plan for a client (confirm-gated). meals: array of MealInput objects (e.g. { name, slot, calories, macros, days }).

Inputs: clientId (required), title (required), startDate (required), meals (required), +2 more.

create_habitCInspect

Create a habit for a client (confirm-gated). daysOfWeek: 0=Sun..6=Sat (empty = every day). reminderTime: 'HH:mm'.

Inputs: clientId (required), name (required), emoji, description, +6 more.

create_master_habitBInspect

Create a reusable Master Habit in the coach's library (confirm-gated).

Inputs: name (required), emoji, description, category, +3 more.

create_workout_planAInspect

Create a workout plan for a client (confirm-gated). exercises: array of { name, sets, reps, restSeconds?, section? }. section must be one of WARMUP | RESISTANCE | STRETCHING | CARDIO | COOL_DOWN (defaults to RESISTANCE so the app renders them under 'Main Workout'). days: optional [MONDAY..SUNDAY].

Inputs: clientId (required), title (required), startDate (required), exercises (required), +4 more.

get_client_profileA
Read-only
Inspect

Get a client's fitness profile + computed metrics (BMI, TDEE, recommended calories). Pass the client's user _id.

Inputs: userId (required).

get_habit_complianceA
Read-only
Inspect

Habit compliance percentage (0-100) for a client over a date range (YYYY-MM-DD).

Inputs: clientId (required), startDate (required), endDate (required).

list_checkinsA
Read-only
Inspect

List check-ins for the coach (optionally filtered to one client by user _id).

Inputs: clientId.

list_client_habitsA
Read-only
Inspect

List a client's active habits with today's log and streaks. Pass the client's user _id as clientId.

Inputs: clientId (required).

list_clientsA
Read-only
Inspect

List the coach's clients (id, name, email). Use the returned _id as clientId/userId for other tools.

Inputs: pageNumber, pageSize.

list_diet_plansA
Read-only
Inspect

List a client's diet plans (id, title, dates). Pass the client's user _id.

Inputs: clientId (required).

list_sessionsA
Read-only
Inspect

List sessions — for one client (pass clientId) or all of the coach's clients.

Inputs: clientId.

list_subscriptionsA
Read-only
Inspect

List the coach's client subscriptions (id, subscriber = client id, status). Use a subscription _id when scheduling a session.

Inputs: no named parameters.

list_workout_plansA
Read-only
Inspect

List a client's workout plans (id, title, dates). Pass the client's user _id.

Inputs: clientId (required).

master_habitsA
Read-only
Inspect

List the coach's reusable Master Habit library.

Inputs: no named parameters.

recent_habit_activityA
Read-only
Inspect

Recent habit completions across all of the coach's clients (newest first).

Inputs: limit.

schedule_sessionAInspect

Book a session for a client (confirm-gated). Needs the client's subscriptionId (see list_subscriptions). Times are ISO strings.

Inputs: clientId (required), subscriptionId (required), scheduledStart (required), scheduledEnd (required), +3 more.

whoamiA
Read-only
Inspect

Return the authenticated coach (user id, name, email, role) and trainer id. Use to verify the connection.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 23 tools

    Disambiguation5/5

    Each tool targets a distinct resource and action. List tools differentiate by entity (clients, check-ins, habits, etc.), create tools are specific, and calc tools serve unique purposes. No two tools have overlapping functionality, making selection unambiguous.

    Naming Consistency4/5

    Most tools follow a consistent verb_noun pattern (e.g., list_clients, create_habit). However, 'master_habits' and 'recent_habit_activity' deviate from the expected 'list_*' prefix, and 'whoami' is a single word, slightly breaking the pattern.

    Tool Count4/5

    23 tools cover a wide range of coaching functionalities (clients, habits, plans, sessions, billing, calculations). While slightly above the typical 3-15 range, each tool serves a distinct purpose and contributes to the server's comprehensive scope.

    Completeness2/5

    The tool surface is heavily skewed toward creation and listing. There are no update or delete operations for any resource (e.g., diet plans, workout plans, habits, sessions), which leaves agents unable to modify or remove existing data, creating significant workflow gaps.

    Maintenance

    ActivityActive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    • tri-train is a training platform for triathletes that syncs activities from Strava and Garmin and exposes them to Claude through a remote MCP server. Ask Claude how your last block went, why your run pace dropped, or whether you are fresh enough for Sunday's race, and it answers from your real data: activities with laps and grade-adjusted pace, weekly load and the performance management chart (CTL/ATL/TSB), sleep, HRV and resting heart rate, and your race calendar with predictions. Claude can also act: create and adjust planned workouts with structured intervals, push them to your Garmin watch, add races and write notes. Every change is journaled and can be undone. Read and write access are separate OAuth scopes, and the server enforces them on every call. Built and hosted in Switzerland by a triathlete; data stays on our own servers (Swiss revDSG / GDPR).

      https://tri-train.com/api/mcp
    • Talk to your own gym log. Reps: Gym Workout Log (repsworkout.com) is a workout log for iPhone and Android. Connect it to Claude, ChatGPT or any MCP client to read your workout history, PRs, lift progression, weekly summaries, routines and training plan, and to save routines and plans after you confirm them. It never logs a workout for you and can’t delete your history. Sign in with an e-mail code, Apple or Google; new users can create a free account while connecting, then get the app to log workouts.

      https://api.repsworkout.com/mcp
    • Trainerize MCP server for ChatGPT, Claude and any AI agent: list clients, assign program, message client, log body stats and schedule appointment in your own Trainerize account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Trainerize yourself; Cotlet does not store your password and you need no Trainerize API key. About the official Trainerize API: Trainerize has an API, but only on Studio and Enterprise plans or with the paid FitMetrics add-on (checked 10 Oct 2026). Grow and Pro trainers get Zapier, not the API, and there is no public API reference. Setup and FAQ: https://cotlet.dev/integrations/trainerize-api-mcp-server

    • Calorie, workout and body-weight log inside ChatGPT and Claude. Log meals by text, photo or voice.

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables workout tracking and coaching within Claude conversations, managing exercise configs, logs, streaks, and health metrics via an MCP server with PostgreSQL.
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      A personal remote MCP server that lets Claude read your Hevy workout data and MacroFactor nutrition data directly in conversation, with read-only tools for workouts, body measurements, macros, and weight trends.
      MIT
    • F
      license
      Not graded
      quality
      A
      maintenance
      Enables Claude and other AI assistants to query and manage an athlete's cycling, running and strength data through secure cookie authentication, with no API approval required. Users can create and schedule structured workouts, edit calendar events and notes, analyze power PRs and CTL/ATL/TSB fitness trends, log health metrics, and manage coach rosters entirely through natural language.
      -