Zenoti MCP Server
Appointments, guests, messages, reviews, sales and staff schedules in Zenoti.
托管 MCP 服务器
npx add-mcp 'https://cotlet.dev/mcp/v1/zenoti'可安装到 Claude Code、Codex、Cursor 等客户端
文档
Cotlet · Integrations · How it works · Security · For developers · For automation agencies · Blog · API docs · Help center · Changelog · Contact · Pricing · Sign up
Zenoti API and MCP server: Let your AI agent work the front desk inbox.
Zenoti documents a REST API and webhooks at docs.zenoti.com, covering centers, guests, appointments, employees and memberships. To use it, a business asks its Zenoti Customer Success Manager to enable the API package, then creates a backend app with an App ID, App Secret and API Key. No Zenoti MCP server or official ChatGPT or Claude connector was verified.
Zenoti's API is open only to businesses with the API package, set up through their Customer Success Manager, and there is no Zenoti MCP server (checked 13 Nov 2026). Cotlet runs a hosted Zenoti MCP server with 20 tools that ChatGPT, Claude and your scripts use from your own employee login. Replies, reviews, broadcasts and bookings wait for your OK.
- Free 7-day trial, no card
- Unofficial, not affiliated with Zenoti
- Page: https://cotlet.dev/integrations/zenoti-api-mcp-server
What can your AI agent do in Zenoti?
- Build the call-back list from abandoned bookings
- Draft replies to the SMS and WhatsApp inbox
- Reply to new Google and Facebook reviews
- Tell booked guests about a closure
- Draft purchase orders for low stock
- Check commission before payroll
Does Zenoti have an MCP server or an API?
- Webhooks notify your own application of events such as a new guest, a membership change or a closed invoice.
- Zeenie and AI Business Advisor are Zenoti's own AI products; AI Business Advisor is a Marketplace add-on that uses credits.
- HyperConnect and ezConnect hold calls, guest messages, reviews and their reports inside Zenoti.
| What you need | Zenoti API | Zeenie / AI Advisor | Cotlet |
|---|---|---|---|
| Ask ChatGPT or Claude to do the work | No MCP server verified | Zenoti's own assistants | Hosted MCP server |
| Start without the vendor | API package through your CSM | Activation or add-on | Your login, once |
| Inbox, reviews and HyperConnect reports | Not in the API index | Answers questions | 20 tools, writes after your OK |
| Run from n8n or a script | After setup, your own code | Inside Zenoti only | REST, same key |
Checked 13 Nov 2026. Sources: Zenoti API: custom sources and API Key, Zenoti Webhooks overview, Zenoti API docs index, Help: AI Business Advisor, Help: Zeenie, Help: Appointments, Help: Queue, Help: Fitness, Help: Loyalty, Help: Messaging and Engagement Tools, Help: HyperConnect, Help: Reports in HyperConnect, Help: Guest Summary in HyperConnect, Help: Manage Social Reviews, Help: SmartBot, Help: Marketing, Help: Point of Sale, Help: Inventory, Help: Employee and payroll, Help: Zenoti Driven Growth dashboard, Help: Kiosk
How does the Zenoti MCP server work?
- Sign in to Zenoti. Once, in a browser we host for you.
- Connect your AI agent. One address in its settings.
- Hand it the inbox. It drafts each reply, you approve it.
Your agent works in your own signed-in Cloud Browser. Anything a guest sees, from a text reply to a review response, waits for your OK.
How to connect Zenoti to your AI agent
- Sign in to Zenoti in a Cloud Browser. Open Zenoti in your Cotlet Cloud Browser and sign in with your own employee login.
- Add the Cotlet address. Enter https://cotlet.dev/mcp/v1 as the MCP server or connector URL in your agent.
- Let the agent in. Chat apps open a Cotlet sign-in page. Editors, n8n and scripts send an API key made in the console.
Zenoti shares https://cotlet.dev/mcp/v1 with every app you turn on in Cotlet, so one connector reaches all of them. Turned Zenoti on after connecting? A connector refresh brings in its 20 tools.
ChatGPT:
Settings > Apps & Connectors > Create
MCP server URL: https://cotlet.dev/mcp/v1/connect
Authentication: OAuth
Claude:
Settings > Connectors > Add custom connector
URL: https://cotlet.dev/mcp/v1/connect
Claude Code:
claude mcp add --transport http cotlet \
https://cotlet.dev/mcp/v1 \
--header "Authorization: Bearer $COTLET_API_KEY"
Cursor:
// ~/.cursor/mcp.json
{
"mcpServers": {
"cotlet": {
"url": "https://cotlet.dev/mcp/v1",
"headers": { "Authorization": "Bearer ${env:COTLET_API_KEY}" }
}
}
}
Codex:
# ~/.codex/config.toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
n8n:
MCP Client Tool (inside an AI Agent)
Transport: HTTP Streamable
URL: https://cotlet.dev/mcp/v1
Auth: Bearer, <your key>
Tool: zenoti_read
All 20 Zenoti MCP tools
One tool per Zenoti Help hub. Read tools run at once. Write tools take an action; list and get only read, the rest change Zenoti and ask first.
Front desk: appointments, queue and classes
The Appointment Book, walk-ins in the Queue, fitness classes and the kiosk.
- Read the appointment book (
view_appointment_book, read): Read a center's appointments for a day: guest, service, provider, time and status. - Book and reschedule appointments (
manage_appointments, write, asks first): Book, reschedule or cancel an appointment in the Appointment Book. - Manage the walk-in queue (
manage_queue, write, asks first): Read the Queue, add a walk-in guest, edit a visit, or send a payment link. - Schedule fitness classes (
manage_classes, write, asks first): Read the class schedule and rosters, schedule a class or workshop, or check guests in. - Set up the kiosk (
configure_kiosk, write, asks first): Read or change kiosk settings: guest actions, wait times and display.
Guests and loyalty
Guest profiles, HyperConnect guest summaries and loyalty points.
- Read a guest summary (
get_guest_summary, read): Read a guest's HyperConnect Guest Summary: Insights, Suggestions and Alerts. - Update guest profiles (
manage_guests, write, asks first): Search guests, add one, update details and labels, or record feedback and issues. - Redeem loyalty points (
manage_loyalty_points, write, asks first): Read a guest's loyalty points and tier, or redeem points.
Conversations and reputation
The ezConnect inbox, SMS broadcasts, Google and Facebook reviews and SmartBot answers. Everything here reaches guests.
- Reply to guest messages (
manage_conversations, write, asks first): Read the ezConnect inbox of SMS, WhatsApp, Facebook Messenger and web chat, reply, or add a private note. - Send SMS broadcasts (
send_broadcast, write, asks first): Send an SMS broadcast to a guest group, for example hour changes or a provider out, and track delivery. - Respond to Google and Facebook reviews (
manage_reviews, write, asks first): Read Google and Facebook reviews in HyperConnect, or post a response. - Update SmartBot FAQs (
manage_smartbot_faqs, write, asks first): List, create, edit or publish the FAQs SmartBot answers guests with.
Sales, marketing and stock
POS invoices, campaigns and discounts, purchase orders and transfers.
- Make sales at the POS (
make_sale, write, asks first): Create a POS invoice for services or products, or sell a membership, package, gift card or prepaid card. - Create campaigns and discounts (
manage_marketing, write, asks first): List or create discounts, campaigns and coupons, target segments, and gift card or loyalty points promotions. - Create purchase orders (
manage_inventory, write, asks first): List or create purchase orders and transfer orders, or record a stock adjustment.
Staff and reporting
Schedules and block-out time, reports, HyperConnect analytics and the growth and fitness dashboards.
- Manage employee schedules (
manage_employee_schedule, write, asks first): Read or change employee schedules, attendance, leave and block-out time. - Run reports (
run_report, read): Run a Zenoti report by name for a center and date range, such as payroll, commission or loyalty points. - Read HyperConnect reports (
view_hyperconnect_reports, read): Read a HyperConnect report or the analytics dashboard for a date range. - Read the Zenoti Driven Growth dashboard (
view_growth_dashboard, read): Read the Zenoti Driven Growth dashboard: capacity, utilization and realization metrics. - Read the fitness dashboard (
view_fitness_dashboard, read): Read the Fitness Dashboard: total sales, membership sales, attendance and new memberships.
Inputs, REST path and example response of every tool: https://cotlet.dev/integrations/zenoti-api-mcp-server#tools
Who can see my Zenoti session, and how do I revoke it?
- What we store. Your signed-in Zenoti browser profile, AES-256-GCM encrypted, in Finland. Never your password.
- What your agent gets. The 20 Zenoti tools. The session cookie stays in the Cloud Browser.
- What the session sees. The centers and screens your employee security role opens, nothing more.
- What no tool touches. Security roles, payroll runs and tip payouts, payment terminals, refunds, Marketplace add-ons and organization settings.
- If Zenoti signs you out. You sign in again yourself, in the same Cloud Browser.
- How to cut access. Disable Zenoti for agents, reset the browser, or change your Zenoti password.
You type your Zenoti password yourself; the agent only uses the session that sign-in leaves behind. Our site scores A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory (live results).
What happens when Zenoti changes?
Zenoti is replacing screens as it goes: the redesigned Appointment Book, the new kiosk on ZMA before the old kiosk retires in July 2026, and HyperConnect beside ezConnect. Cotlet follows those screens, and your agent keeps the same tool names.
Modules that Zenoti enables per business, such as Queue, fitness, HyperConnect or the growth dashboard, are there for the agent only when your business has them.
If Zenoti signs you out, one click in the Cotlet console reopens the Cloud Browser so you can sign in again.
Approvals, undo and mistakes
- Read the message. manage_conversations opens the thread.
- Find the slot. view_appointment_book checks the day.
- Show you both. The move and the reply, side by side.
- Act after your OK. manage_appointments moves it, then the reply goes.
| Action | How to put it right |
|---|---|
| Appointment moved to the wrong slot | Reschedule it back with manage_appointments |
| Guest profile field changed | Call manage_guests again with the earlier value |
| Purchase order drafted | Still a draft: change it in Zenoti with your purchasing team |
| Reply, review response or broadcast sent | Already with the guest or public: follow up yourself |
All 14 write tools ask first: by default you confirm each call, and you can switch that off per tool. The 6 read tools, from the Appointment Book to the dashboards, run at once.
MCP call:
{
"name": "manage_appointments",
"arguments": {
"action": "reschedule",
"center": "Downtown",
"appointment_id": "apt_88213",
"start": "2026-11-21T11:00"
}
}
REST:
curl -X POST https://cotlet.dev/api/v1/zenoti/appointments/manage \
-H "Authorization: Bearer $COTLET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"action":"reschedule","center":"Downtown","appointment_id":"apt_88213","start":"2026-11-21T11:00"}'
Response:
{
"appointment_id": "apt_88213",
"guest": "Example Guest",
"service": "Signature Facial",
"employee": "Provider A",
"start": "2026-11-21T11:00",
"status": "Booked"
}
The example moves Example Guest's Signature Facial to Saturday at 11:00 with the same provider. A cron job or n8n flow can make the same call over REST at /api/v1/zenoti with the same key and price, in JSON. Failed calls are free.
How much does the Zenoti MCP server cost?
About $25 a month for a day spa with two centers, 4,280 credits. Your Zenoti subscription stays as it is.
| Job | Calls | Credits |
|---|---|---|
| Abandoned bookings call list | 4 × 22 | 880 |
| Guest inbox replies | 1 × 80 | 800 |
| Reschedules from the inbox | 1 × 40 | 400 |
| Guest profile updates | 1 × 30 | 300 |
| Review replies | 1 × 20 | 200 |
| Weekly commission report, two centers | 2 × 4 | 80 |
| Purchase orders | 2 × 4 | 80 |
| SMS broadcasts | 2 × 2 | 40 |
| Cloud Browser, 30 days | 1,500 | |
| Total | 278 calls | 4,280 |
The smallest pack, 5,000 credits for $29, covers this month. A busier inbox or more centers mean more calls.
- Free 7-day trial, no card
- 10 credits per successful call, MCP or REST
- 50 credits a day for the Cloud Browser
- No API package needed for Cotlet
Credit packs are one-time purchases, not a subscription. The month above is built from our own assumptions, not measured customer usage.
Zenoti MCP server: other ways to connect
| Option | What it does | Where it stops |
|---|---|---|
| Zenoti API and webhooks | Documented REST endpoints and event notifications for your own code. | API package through your CSM; your developers build and host it. |
| Zeenie | Zenoti's assistant for help articles, insights and front desk support. | Inside Zenoti; not a connector for ChatGPT or Claude. |
| AI Business Advisor | Plain-English KPI answers and dashboards from your Zenoti data. | Marketplace add-on with credits; answers, does not act. |
| By hand | Work each inbox, report and review in Zenoti. | One screen at a time, between guests. |
If your business has the API package and developers for the job, use the API: it is Zenoti's own route. Cotlet fits when you want ChatGPT, Claude or a script working in Zenoti today from your login, including the inbox and review screens, with nothing to host.
Who runs Cotlet
Behind Cotlet is Take Group sp. z o.o., a software company registered in Poland, EU (VAT PL6342984273), in business since 2019 and led by Bart Krawczyk (Co-founder, CTO) and Jake Slugocki (Co-founder, SEO, sales and marketing). Questions about the Zenoti tools: contact@cotlet.dev.
Zenoti MCP server: questions
How do I get access?
Sign up free at https://cotlet.dev/signup?app=zenoti, turn on Zenoti under Integrations in the console and sign in to Zenoti in your Cloud Browser. Then connect your AI agent and ask it about today's appointment book. The trial needs no card.
Does Zenoti have an API?
Zenoti documents a REST API and webhooks at docs.zenoti.com for centers, guests, appointments, employees and memberships, but a business needs the API package, enabled through its Zenoti Customer Success Manager, plus a backend app with App ID, App Secret and API Key (checked 13 Nov 2026). No Zenoti MCP server or official ChatGPT or Claude connector was verified. Cotlet does not need the API package: it works in your own signed-in Zenoti account.
How is this different from Zeenie or AI Business Advisor?
Zeenie and AI Business Advisor are Zenoti's own AI products inside Zenoti; AI Business Advisor is an add-on from the Zenoti Marketplace that uses credits. Cotlet is separate: it lets ChatGPT, Claude or a script you choose work in Zenoti with the tools on this page.
Which centers can the agent see?
The centers and screens your login's security role opens. A login limited to one center gives the agent one center; an organization-level role gives it more.
Do I need the API package?
Not for Cotlet. The API package is for Zenoti's own API; Cotlet works through your employee login, so the tools reach what your security role reaches.
Is the MCP server different from the REST API?
Only in how it is called. Both carry the same 20 tools, inputs, answers, API key and price. Agents use MCP; scripts and n8n HTTP steps use REST.
Is Cotlet affiliated with Zenoti?
No. Cotlet is independent and not affiliated with Zenoti.
Give your AI agents your signed-in browser.
Product: Integrations · How it works · Pricing · Security
Resources: Blog · API docs · Help center · Changelog · GitHub
Solutions: For developers · For automation agencies
Company: About · AI info: company facts · Contact
Legal: Terms of service · Privacy policy · Refund policy · Acceptable use · Cookie policy · DPA · Subprocessors
Elsewhere: Status page · Cotlet on GitHub · Cotlet on X · Cotlet on LinkedIn · Cotlet on Product Hunt · Cotlet on Crunchbase · Cotlet on SaaSHub
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
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.