Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@clubready-mcp Find the customer profile for Sarah in my authorized club."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Connect ClubReady to ChatGPT, Claude and other AI agents through Cotlet. Work in your own signed-in ClubReady account, with access controlled by your club role. Cotlet is independent and is not affiliated with ClubReady.
Search customer or prospect profiles in my authorized club.
Show the customer profile for the member I select.
Prepare an update to a selected customer’s business contact details and show it before saving.
Check the membership type for the customer I select and show any entitlement change before approval.
Related MCP server: Open ChatGPT
Get your API key at https://cotlet.dev/app and export it as COTLET_API_KEY.
Add https://cotlet.dev/mcp/v1 as a custom connector in Claude and sign in with Cotlet.dev.
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"Settings → Apps → add connector URL https://cotlet.dev/mcp/v1, then sign in with Cotlet.dev. No API key needed.
Copy .cursor/mcp.json from this repo into your project:
{
"mcpServers": {
"cotlet": {
"url": "https://cotlet.dev/mcp/v1",
"headers": {
"Authorization": "Bearer ${COTLET_API_KEY}"
}
}
}
}This repo is a real MCP server. It speaks MCP over stdio, lists its ClubReady tools without any key, and forwards every tool call to the hosted Cotlet.dev server. The hosted URL above stays the recommended way. Use this when your client only starts local servers.
{"mcpServers":{"clubready":{"command":"uvx","args":["clubready-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}Or with Docker:
docker build -t clubready-mcp .
docker run -i --rm -e COTLET_API_KEY clubready-mcpTools: clubready_guide, clubready_status, clubready_open, clubready_read, clubready_click, clubready_type, clubready_close. Without COTLET_API_KEY a tool call answers: "Set COTLET_API_KEY. Get a key at https://cotlet.dev/app".
Python 3.10+, nothing else to install. From PyPI:
pip install clubready-mcp # or run it once: uvx clubready-mcp connect
clubready-mcp connectOr straight from this repo:
export COTLET_API_KEY="your-key"
python3 clubready_agent.py connect # ready config for Claude Code, Cursor, ChatGPT
python3 clubready_agent.py status # is ClubReady ready in your Cotlet.dev account
python3 clubready_agent.py guide # ClubReady screens and sign-in link
python3 clubready_agent.py read # open ClubReady, read the page, close the browser
python3 clubready_agent.py tools # list Cotlet.dev tools
python3 clubready_agent.py serve # start the stdio MCP server (same as no argument)How do I get access?
Create a Cotlet account, open ClubReady and sign in at app.clubready.com/login. Enable it for agents, then add Cotlet to your chosen AI assistant.
How do I connect ClubReady to ChatGPT or Claude?
Sign up at cotlet.dev, log in to ClubReady once in its Cloud Browser and add Cotlet to ChatGPT or Claude, following the steps in your console. No API key is needed. ChatGPT and Claude then work in your ClubReady account through Cotlet, in their phone apps too.
What can ChatGPT do in ClubReady?
With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in ClubReady: search customer or prospect profiles; view a customer profile; view customer amenities. You ask in plain words.
Is there an official ChatGPT or Claude app for ClubReady?
No vendor-published ClubReady MCP server or ChatGPT or Claude connector was found in the sources checked on 12 November 2026. Cotlet is independent and is not affiliated with ClubReady.
Does ClubReady have an API?
ClubReady provides an official API and real-time data notifications. Request a key from ClubReady Support; third-party authorization is approved by the club owner.
Is the MCP server different from the REST API?
Only in how it is called. Both carry the same 168 tools, inputs, answers, API key and price. Agents use MCP; scripts and HTTP steps use REST.
Is Cotlet affiliated with ClubReady?
No. Cotlet is independent and not affiliated with ClubReady.
Request access: https://cotlet.dev/signup?app=clubready&utm_source=github&utm_medium=readme&utm_campaign=clubready
Click a numbered element on the current ClubReady page.
Inputs: element (required).
Close the ClubReady browser session when the work is done, so credits stop running.
Inputs: no named parameters.
How to work in ClubReady (manage customer profiles, memberships and club operations): its screens and the sign-in link. Call this first.
Inputs: task.
Open a ClubReady page in your signed-in Cloud Browser (default https://app.clubready.com) to work with manage customer profiles, memberships and club operations.
Inputs: url.
Read the current ClubReady page: its text and numbered buttons, links and fields.
Inputs: element.
Check that your Cotlet.dev account and ClubReady are ready: account, credits and ClubReady connection.
Inputs: no named parameters.
Type text into a numbered field on the current ClubReady page.
Inputs: text (required), element (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 7 tools
The core interaction tools (open, read, click, type, close) map to clearly distinct browser actions with no overlap. The only mild ambiguity is between clubready_guide (how-to/onboarding) and clubready_status (account/connection readiness), but their descriptions draw a usable line between instructions and diagnostics.
Every tool uses the same clubready_ prefix with a single lowercase verb-style suffix (guide, status, open, read, click, type, close). The pattern is fully predictable and consistent throughout.
Seven tools is well-scoped for a browser-session wrapper: onboarding/status, session lifecycle, and the four core page-interaction primitives. Each tool earns its place with no filler.
The lifecycle (open → read → click/type → close) plus status/guide covers basic workflows, but common web-form needs are absent: no scrolling, key presses (e.g. Enter), dropdown/select handling, or back/navigate control beyond opening a page. Agents may hit dead ends on longer pages or complex membership forms.
Glofox MCP server for ChatGPT, Claude and any AI agent: book member into class, list classes, list members, add lead and check in member in your own Glofox account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Glofox yourself; Cotlet does not store your password and you need no Glofox API key. About the official Glofox API: Glofox has a REST API for members, memberships, classes, bookings and payments, but the key and token come only on request to ABC Fitness, and its Zapier app needs the Elite plan (checked 8 Nov 2026). It has no official MCP server. Setup and FAQ: https://cotlet.dev/integrations/glofox-api-mcp-server
FitBudd MCP server for ChatGPT, Claude and any AI agent: add client, schedule workout, review check-ins, add client note and list clients in your own FitBudd account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to FitBudd yourself; Cotlet does not store your password and you need no FitBudd API key. About the official FitBudd API: FitBudd publishes no public API; its developer docs return "gone". Its only connection is a Zapier app with triggers only, on the Super Pro plan and higher (checked 9 Nov 2026). Setup and FAQ: https://cotlet.dev/integrations/fitbudd-api-mcp-server
PushPress MCP server for ChatGPT, Claude and any AI agent: list members, book class reservation, check in member, cancel reservation and update membership plan in your own PushPress account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to PushPress yourself; Cotlet does not store your password and you need no PushPress API key. About the official PushPress API: PushPress has a Platform API and an SDK that doubles as a local MCP server, both using an API key from Settings > Security & Access, but they are mostly read-only beyond creating customers and invitations (checked 11 Oct 2026). Booking, check-ins, plan changes and class cancellations are done by staff in Core. Setup and FAQ: https://cotlet.dev/integrations/pushpress-api-mcp-server
Mariana Tek MCP server for ChatGPT, Claude and any AI agent: list classes, book reservation, cancel reservation, find customer and add class credits in your own Mariana Tek account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Mariana Tek yourself; Cotlet does not store your password and you need no Mariana Tek API key. About the official Mariana Tek API: Yes, but gated: Mariana Tek has APIs (Customer, Studio, Admin, Webhooks and more), and credentials go only to integration partners who sign the Developer Tools Terms of Service and to developers working with a single studio, with the studio owner included in the request; no official MCP server exists (checked 11 Oct 2026). A technical review of about 1 to 3 weeks may follow, and reporting data and Stripe data are not available through the API. Setup and FAQ: https://cotlet.dev/integrations/mariana-tek-api-mcp-server
