[Cotlet](https://cotlet.dev/index.md) · [Integrations](https://cotlet.dev/integrations.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Security](https://cotlet.dev/security.md) · [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md) · [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [Contact](https://cotlet.dev/contact.md) · [Pricing](https://cotlet.dev/pricing.md) · [Sign up](https://cotlet.dev/signup)

# How to connect Trainerize to ChatGPT, Claude and AI agents

> Trainerize describes an official FitMetrics MCP for ChatGPT and Claude (12 Nov 2026); API access needs Studio, Enterprise or FitMetrics. Compare Cotlet.

Source: https://cotlet.dev/blog/how-to-connect-trainerize-to-chatgpt-claude

Trainerize describes an official FitMetrics MCP for ChatGPT and Claude (12 Nov 2026); API access needs Studio, Enterprise or FitMetrics. Compare Cotlet.

Cotlet team · Nov 12, 2026 · 11 min read

On this page

1. [01 What ChatGPT and Claude can do in Trainerize once connected](#what-chatgpt-and-claude-can-do-in-trainerize-once-connected)
2. [02 Does Trainerize have AI, an API or an official ChatGPT app?](#does-trainerize-have-ai-an-api-or-an-official-chatgpt-app)
3. [03 Set up the coach account you intend to use](#set-up-the-coach-account-you-intend-to-use)
4. [04 Step 1: sign in to Trainerize in your Cloud Browser](#step-1-sign-in-to-trainerize-in-your-cloud-browser)
5. [05 Step 2: connect Trainerize to ChatGPT, Claude or another AI agent](#step-2-connect-trainerize-to-chatgpt-claude-or-another-ai-agent)
6. [06 Three Trainerize jobs to try first](#three-trainerize-jobs-to-try-first)  
  1. [Review submitted check-ins before writing replies](#review-submitted-check-ins-before-writing-replies)
  2. [Reconcile missing progress entries](#reconcile-missing-progress-entries)
  3. [Prepare a program transition with the current assignment visible](#prepare-a-program-transition-with-the-current-assignment-visible)
7. [07 Keep the two costs separate](#keep-the-two-costs-separate)
8. [08 FAQ](#faq)  
  1. [Can Trainerize connect to ChatGPT or Claude officially?](#can-trainerize-connect-to-chatgpt-or-claude-officially)
  2. [Does Trainerize have an API or an MCP server?](#does-trainerize-have-an-api-or-an-mcp-server)
  3. [Can Zapier, Make or n8n automate Trainerize?](#can-zapier-make-or-n8n-automate-trainerize)
  4. [Is the FitMetrics MCP server operated by Trainerize?](#is-the-fitmetrics-mcp-server-operated-by-trainerize)
  5. [Does connecting an assistant send check-in replies automatically?](#does-connecting-an-assistant-send-check-in-replies-automatically)
9. [09 Start with one coaching review](#start-with-one-coaching-review)

Trainerize describes a FitMetrics MCP connection for ChatGPT and Claude in its [November update](https://www.trainerize.com/blog/new-abc-trainerize-updates-coach-more-flexibly-stay-connected-and-get-more-done-with-ai-tools-you-already-use/), checked 12 November 2026, for client and business workflows. API and webhook access depends on a Studio, Enterprise or FitMetrics entitlement, according to its [API guide](https://help.trainerize.com/hc/en-us/articles/37082084919060-Using-API-and-Webhooks-With-ABC-Trainerize). To connect Trainerize through Cotlet instead, sign in with your coach account in your Cloud Browser and add Cotlet to your assistant; its [14 Trainerize tools](https://cotlet.dev/integrations/trainerize-api-mcp-server.md) work through your own account’s screens. This guide helps you compare the documented routes before handing over check-ins, program admin or appointments.

The reader here is the coach running a roster, not a client logging a workout. You may already have a useful assistant for explaining a training block. The next question is whether it can read the right client records and do the admin inside your actual coaching account. Cotlet is for the coach or studio operator who wants to delegate that account work from the AI they already use.

## What ChatGPT and Claude can do in Trainerize once connected

Use the client’s name or identifier and the period you mean. “Check progress” should become a defined review of the check-ins, messages or records the account can access. A request to prepare a reply is different from permission to send it.

| Coaching admin | A useful instruction |
| -------------- | ------------------------------------------------------------ |
| Roster | Find clients matching the status you specify |
| Check-ins | Review submissions and draft your response |
| Progress | Read the recorded entries for a defined period |
| Programs | Review the current assignment before proposing a replacement |
| Messages | Prepare a client-specific message for approval |
| Appointments | Review availability and the booking change you request |

The [Trainerize API and MCP page](https://cotlet.dev/integrations/trainerize-api-mcp-server.md) explains the Cotlet route. It works through the screens your signed-in account can access. Calls marked **Asks first** wait for approval by default, and you can disable confirmation per tool. Keep clinical judgment, client consent and any account-level settings with the responsible person.

## Does Trainerize have AI, an API or an official ChatGPT app?

Trainerize describes a FitMetrics MCP connection for ChatGPT and Claude in its [November announcement](https://www.trainerize.com/blog/new-abc-trainerize-updates-coach-more-flexibly-stay-connected-and-get-more-done-with-ai-tools-you-already-use/), checked 12 Nov 2026\. Its [API and webhooks](https://help.trainerize.com/hc/en-us/articles/37082084919060-Using-API-and-Webhooks-With-ABC-Trainerize) have access conditions for Studio, Enterprise and FitMetrics. Cotlet runs a hosted Trainerize MCP server, <https://cotlet.dev/mcp/v1/trainerize>, with 14 tools your agent uses in your own account.

- **FitMetrics:** the announcement describes more than 220 actions, confirmation before writes, impact previews, audit trails and coach-level scoping.
- **Zapier:** [ABC Trainerize’s connector](https://zapier.com/apps/abc-trainerize/integrations) supports its published triggers and actions.
- **Product Automation:** [configured delivery rules](https://help.trainerize.com/hc/en-us/articles/39988722481044-Automating-Content-Delivery-with-Product-Automation) send content tied to purchased products.

Among these routes, Cotlet gives ChatGPT, Claude or any MCP client read and write access through the Trainerize screens your coach account can use, without a Trainerize API key or an API-entitlement upgrade.

## Set up the coach account you intend to use

- Use your coach or authorized studio account, with access to the relevant clients.
- Have the client identifier and review period ready for the first task.
- Decide whether you need a draft, an account edit or a message sent to a client.
- Keep your existing ChatGPT or Claude account available and create a Cotlet account.

## Step 1: sign in to Trainerize in your Cloud Browser

Open Trainerize from Cotlet and use **trainerize.com/login** or the studio’s normal branded login. Select the coach workspace you mean to delegate. Before asking for a roster review, confirm that this login sees that roster and is not a separate client account.

Cotlet never sees or stores your password. Its encrypted Cloud Browser profile keeps the sign-in available for your next task; the [security page](https://cotlet.dev/security.md) describes this design. If Trainerize requests another sign-in, reopen the Cloud Browser and complete it yourself. Your assistant should not change account credentials or subscription settings as part of a check-in review.

## Step 2: connect Trainerize to ChatGPT, Claude or another AI agent

Select your assistant below. Make the first question a client lookup that you can recognize, then move to the check-in workflow after confirming the account and period.

**ChatGPT**chatgpt.com and its apps **Claude**claude.ai and desktop app **Claude Code**one terminal command **Codex**one entry in config.toml **Cursor**one entry in mcp.json **Grok**grok.com connectors **Hermes Agent**one block in config.yaml **n8n**MCP Client node **Any MCP client**OpenClaw and others

Pick your AI above to see its steps.

### How to connect Trainerize to ChatGPT

Do this on chatgpt.com in your browser. Cotlet then works in the ChatGPT desktop and phone apps too.

1. Open [Plugins in ChatGPT](https://chatgpt.com/plugins) and click Add.
2. Click Add custom MCP server. Not in the menu? Turn on Developer mode in Settings, Security and login, then come back.
3. Paste the name `Cotlet` and the server URL `https://cotlet.dev/mcp/v1/connect`. Keep Authentication on OAuth.
4. Tick “I understand and want to continue” and click Create as a plugin.
5. Click Connect Cotlet. A Cotlet page opens, click Allow access.
6. In a new chat, type `@Cotlet` and pick it from the list.
7. Ask ChatGPT: “Are you signed in to Cotlet through MCP?” Then try a first Trainerize task: “Find this week’s submitted check-ins in my Trainerize coach account. Show client and submission date. Do not send messages.”

_ChatGPT, bottom of the custom MCP server form, November 2026._

_ChatGPT, picking Cotlet in a new chat with @, November 2026._

ChatGPT asks “Allow ChatGPT to use Cotlet?” before some steps. Pick Always allow, or the chat waits for your click. On a Business, Enterprise or Edu workspace, an admin has to allow custom MCP servers first.

### How to connect Trainerize to Claude

1. Open [Connectors in Claude](https://claude.ai/customize/connectors) and click Add. In the desktop app it is under Customize, Connectors.
2. Click Add custom connector.
3. Paste the name `Cotlet` and the URL `https://cotlet.dev/mcp/v1/connect`, then click Continue.
4. Keep the settings and click Add.
5. A Cotlet page opens. Click Allow access.
6. In a chat, click the plus button, then Connectors, and turn Cotlet on.
7. Ask Claude: “Are you signed in to Cotlet through MCP?”, then “Read the current Trainerize program assignment for the client I select and show its end date before proposing any change.”. Claude asks before it uses a Cotlet tool the first time. Click Allow.

_Claude, Add custom connector form, November 2026._

_Cotlet consent page after you add the connector in Claude, November 2026._

Claude’s free plan allows one custom connector. On a Team or Enterprise plan, an owner adds Cotlet in Organization settings, Connectors, and you click Connect next to it.

### How to connect Trainerize to Claude Code

Add Cotlet without a key, then sign in once in the browser:

```
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1/connect
```

Run `/mcp` in Claude Code, pick cotlet and sign in to Cotlet. Prefer an API key, for example on a server? Create one in the Cotlet console and use:

```
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 \
  --header "Authorization: Bearer $COTLET_API_KEY"
```

### How to connect Trainerize to Codex

Create an API key in the Cotlet console, put it in the `COTLET_API_KEY` environment variable and add this to `~/.codex/config.toml`:

```
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
```

### How to connect Trainerize to Cursor

Create an API key in the Cotlet console, put it in the `COTLET_API_KEY` environment variable and add this to `~/.cursor/mcp.json`:

```
{
"mcpServers": {
"cotlet": {
"url": "https://cotlet.dev/mcp/v1",
"headers": { "Authorization": "Bearer ${env:COTLET_API_KEY}" }
}
}
}
```

### How to connect Trainerize to Grok

Grok takes custom MCP servers on grok.com, per xAI’s [connectors documentation](https://docs.x.ai/grok/connectors) (checked 8 November 2026).

1. Open [grok.com/connectors](https://grok.com/connectors) and click New Connector.
2. Pick Custom and paste the server URL `https://cotlet.dev/mcp/v1/connect`.
3. Sign in to Cotlet when Grok asks, then click Allow access.
4. Ask Grok: “Are you signed in to Cotlet through MCP?”

On Grok Business, an admin adds the connector first in the xAI console, under Grok Business, Connectors. The Grok chat inside X has no custom connector menu.

### How to connect Trainerize to Hermes Agent

Add Cotlet to `~/.hermes/config.yaml` in the format of the [Hermes MCP config reference](https://hermes-agent.nousresearch.com/docs/reference/mcp-config-reference):

```
mcp_servers:
cotlet:
url: "https://cotlet.dev/mcp/v1"
headers:
Authorization: "Bearer ${COTLET_API_KEY}"
trust: untrusted
```

Put `COTLET_API_KEY` in `~/.hermes/.env` and check it with `hermes mcp test cotlet`. With `trust: untrusted`, Hermes runs reads at once and asks before every write. More on Hermes in our post on the [Hermes Agent browser](https://cotlet.dev/blog/hermes-agent-browser.md).

### How to connect Trainerize to n8n

Use the MCP Client node, or the MCP Client Tool inside an AI Agent node:

- Server Transport: HTTP Streamable
- MCP Endpoint URL: `https://cotlet.dev/mcp/v1`
- Authentication: Bearer Auth, with your Cotlet API key as the token Let the AI Agent node use Cotlet’s browser tools and read the Trainerize guide before navigating the coaching account.

Each Thursday, prepare a coach-only report separating submitted Trainerize check-ins from missing submissions, with draft replies kept unsent.

### Any other MCP client

Point the client at `https://cotlet.dev/mcp/v1` over Streamable HTTP, with the header `Authorization: Bearer <your Cotlet API key>`. A client that supports OAuth sign-in can use `https://cotlet.dev/mcp/v1/connect` instead and needs no key. The full reference is in the [MCP docs](https://cotlet.dev/docs/mcp.md).

## Three Trainerize jobs to try first

### Review submitted check-ins before writing replies

> Review this week’s submitted check-ins for my selected clients. For each one, quote the concern that needs my attention and draft a short response. Separate a missing submission from a submission reporting a problem. Do not send anything.

Trainerize’s [check-in form guidance](https://help.trainerize.com/hc/en-us/articles/31369316335124-Sharing-Check-In-Forms-with-Clients) describes the form workflow. A reminder or notification is different from a coach’s review of what somebody actually wrote. The assistant should report the source record and date rather than collapsing everything into an invented adherence score.

Read the drafts as the coach. A statement about pain, medication or an injury needs your professional response; it is not a reason for an assistant to invent a diagnosis. Approve the specific message only after deciding how you want to respond.

### Reconcile missing progress entries

> Read the body-stat entries for the review period I specify. List clients with no entry, show each last recorded date and draft a neutral reminder for me. Do not treat missing data as a change in body composition.

The [body-stat instructions](https://help.trainerize.com/hc/en-us/articles/208689176-Entering-Body-Stats) distinguish recorded measurements from reminders. The [Insights Dashboard](https://help.trainerize.com/hc/en-us/articles/46648417703956-Using-the-Client-Insights-Dashboard) gives another view of client records. Your useful output is the missing-data list, not a fabricated measurement.

If you compare this with a direct API integration, check the API’s documented history window and your entitlement. Cotlet reads the entries visible to your signed-in role; it should state when a requested period is unavailable instead of silently shortening the review.

### Prepare a program transition with the current assignment visible

> Find the current program for the client I select. Compare its end date with the next block in my notes. Show the existing assignment, the proposed next program and the effective date. Wait for my decision before changing it.

The assistant first establishes what the client already has. Your notes should name the actual program and timing; a broad instruction to “progress everyone” is not enough to choose a training prescription. Check the proposed transition against the client’s situation, then approve the change you want.

For routine delivery tied to a purchased product, Trainerize’s own [Product Automation](https://help.trainerize.com/hc/en-us/articles/39988722481044-Automating-Content-Delivery-with-Product-Automation) may already cover the configured sequence. Cotlet adds a conversational way to inspect the surrounding account and perform the screen work you request.

## Keep the two costs separate

Your Trainerize subscription and any FitMetrics entitlement are vendor costs. Cotlet has its own [credit pricing](https://cotlet.dev/pricing.md): a 7-day trial with 2,000 credits and no card, then packs from $29 with 12-month validity and no Cotlet subscription. Using Cotlet does not require changing your Trainerize plan just to obtain an API key; your existing plan still determines which Trainerize features your account can see.

## FAQ

### Can Trainerize connect to ChatGPT or Claude officially?

Yes. Trainerize describes a FitMetrics MCP connection for both assistants (checked 12 Nov 2026). Compare the [announced FitMetrics actions](https://www.trainerize.com/blog/new-abc-trainerize-updates-coach-more-flexibly-stay-connected-and-get-more-done-with-ai-tools-you-already-use/) with your coaching task. Cotlet is a separate route and is not affiliated with ABC Trainerize or FitMetrics.

### Does Trainerize have an API or an MCP server?

The API and webhooks depend on Studio, Enterprise or FitMetrics entitlement, set out in the [API guide](https://help.trainerize.com/hc/en-us/articles/37082084919060-Using-API-and-Webhooks-With-ABC-Trainerize); a public article about the API is not a grant of access to every account. For MCP, FitMetrics is the described route, and Cotlet hosts <https://cotlet.dev/mcp/v1/trainerize> with 14 tools (checked 12 Nov 2026).

### Can Zapier, Make or n8n automate Trainerize?

[ABC Trainerize’s Zapier connector](https://zapier.com/apps/abc-trainerize/integrations) supports its published client, tag, group and program triggers and actions, and the [API guide](https://help.trainerize.com/hc/en-us/articles/37082084919060-Using-API-and-Webhooks-With-ABC-Trainerize) lists Zapier as automation without API access. Its actions do not read check-ins or appointments. No n8n node was found in the sources checked for this guide, and a Make listing could not be checked.

### Is the FitMetrics MCP server operated by Trainerize?

The checked Trainerize announcement endorses and describes the FitMetrics connection, and its [FitMetrics article](https://help.trainerize.com/hc/en-us/articles/53910982146708-What-Is-FitMetrics-in-ABC-Trainerize) explains the add-on. It does not, by itself, establish who operates every part of that server. Call it the FitMetrics connection described by Trainerize, rather than inventing an ownership claim.

### Does connecting an assistant send check-in replies automatically?

A request to review forms can produce drafts without sending them. In Cotlet, calls marked Asks first require confirmation by default. State the client, recipient and final text before approving a send.

## Start with one coaching review

[Connect your Trainerize account](https://cotlet.dev/signup?app=trainerize) and ask for one defined check-in period. You should recognize the clients, dates and quoted concerns before delegating a change. That makes the first useful result a review you can coach from, rather than another ungrounded summary of your roster.

## Keep reading

[All posts](https://cotlet.dev/blog.md)

- [Agents Nov 17, 2026 How to connect CapCut with an AI agent: automate your work CapCut publishes no MCP address for Claude or Cursor (checked 6 Nov 2026). Here is how to connect your AI agent to CapCut anyway. Cotlet team · 15 min read](https://cotlet.dev/blog/how-to-connect-capcut-to-chatgpt-claude.md)
- [Agents Nov 17, 2026 How to connect Google Discover to an AI agent like ChatGPT or Claude Google has no official MCP server or API for the Discover feed (checked 25 Oct 2026). Connect ChatGPT or Claude with Cotlet.dev. Cotlet team · 15 min read](https://cotlet.dev/blog/how-to-connect-google-discover-to-chatgpt-claude.md)
- [Agents Nov 17, 2026 How to connect PhotoShelter to AI agents and automate the busywork PhotoShelter has no official MCP server or ChatGPT or Claude app (checked 8 Nov 2026). Connect any AI agent to your account through Cotlet.dev. Cotlet team · 15 min read](https://cotlet.dev/blog/how-to-connect-photoshelter-to-chatgpt-claude.md)

## Have an app in mind?

Sign up and add it in the console. Not in the list? Ask for it there.

[Sign up free](https://cotlet.dev/signup)

---

Give your AI agents your signed-in browser.

**Product:** [Integrations](https://cotlet.dev/integrations.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Pricing](https://cotlet.dev/pricing.md) · [Security](https://cotlet.dev/security.md)

**Resources:** [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [GitHub](https://github.com/cotletdev/cotlet)

**Solutions:** [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md)

**Company:** [About](https://cotlet.dev/about.md) · [AI info: company facts](https://cotlet.dev/ai-info.md) · [Contact](https://cotlet.dev/contact.md)

**Legal:** [Terms of service](https://cotlet.dev/terms) · [Privacy policy](https://cotlet.dev/privacy) · [Refund policy](https://cotlet.dev/refunds) · [Acceptable use](https://cotlet.dev/acceptable-use) · [Cookie policy](https://cotlet.dev/cookies) · [DPA](https://cotlet.dev/dpa) · [Subprocessors](https://cotlet.dev/subprocessors)

**Elsewhere:** [Status page](https://status.cotlet.dev) · [Cotlet on GitHub](https://github.com/cotletdev) · [Cotlet on X](https://x.com/cotletdev) · [Cotlet on LinkedIn](https://www.linkedin.com/company/cotletdev) · [Cotlet on Product Hunt](https://www.producthunt.com/products/cotlet) · [Cotlet on Crunchbase](https://www.crunchbase.com/organization/cotlet) · [Cotlet on SaaSHub](https://www.saashub.com/cotlet)

Cotlet.dev is built by Bart Krawczyk and Jake Slugocki, the founders of Take Group sp. z o.o., ul. Wincentego Janasa 4, 40-855 Katowice, Poland. KRS 0000871398, NIP 6342984273, VAT EU: PL6342984273. [About us](https://cotlet.dev/about.md)

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.
