Live

Mangomint logo

Mangomint API and MCP server

mangomint.com

Mangomint has no public API and no developer docs (checked 11 Oct 2026). Cotlet is a hosted MCP server and REST API for Mangomint with 13 endpoints (8 read, 5 write): your AI agent signs in as you and does the work.

Endpoints
13 8 read, 5 write
Updated
How Cotlet connects your agent to Mangomint
  1. Your agent

    Claude Code, Codex, Cursor or a script

  2. Cotlet

    MCP server and REST API · 13 endpoints

    cotlet.dev/mcp/v1

  3. Mangomint logo

    Mangomint

    Signed in as you on mangomint.com

You sign in once. We never store your password.

Official API

Does Mangomint have an official API?

Mangomint has no public API and no developer docs (checked 11 Oct 2026). Its Integrations page lists Shopify, Mailchimp, Webhooks, Docovia and Doxy.me; Webhooks only send event data out (appointments, sales, forms, memberships), so nothing can read your calendar on demand or book, move or cancel an appointment.

What Mangomint's own tools do compared with Cotlet
Task Mangomint official Cotlet
List appointments for a day No Webhooks send an event when an appointment is created, updated or deleted, not a calendar read Yes
Book an appointment No Yes
Reschedule or cancel an appointment No Yes
Find a client and read their timeline No Yes
Book an opening from the waitlist No Yes
Pull a sales or retention report No Webhooks send each completed sale, not a report Yes
Export the client list No Yes
Get notified of new bookings and sales Partly Outbound webhooks, set up through chat support Yes

Sources: Mangomint Integrations · Mangomint Learning Center: Webhooks Integration · Mangomint Learning Center: List of Available Reports · Mangomint Learning Center: Booking an Appointment from the Waitlist · Mangomint Learning Center: Automated Messages, Waitlist Entries

Common use cases

What can an AI agent do in Mangomint?

Cotlet is best for salon and spa owners and front-desk managers who want an AI agent to book, move and report on Mangomint appointments without running or fixing a server.

  • Reschedule appointments when staff is out Runs: Daily

    Alex is out sick today. Move her appointments to tomorrow at the same times, or to another stylist who does the same service today, and tell me which ones didn't fit. Your agent calls list_appointments, list_services and reschedule_appointment.

  • Book a client from the waitlist Runs: Daily

    Check this week's waitlist, show me which entries have an opening, and book each one with the client's requested stylist once I confirm. Your agent calls list_waitlist, get_client_timeline, list_appointments and book_from_waitlist.

  • Weekly sales and cancellations report Runs: Weekly

    Every Monday, send me last week's Sales Summary next to the week before, sales by staff, and the late cancellations and no-shows with no next appointment. Your agent calls list_locations and get_report.

  • Book an appointment from a text or DM

    Jamie texted asking for a signature facial with Alex next Friday afternoon. Find her, check Alex's day and book the first free slot after 1pm. Your agent calls find_client, list_services, list_appointments and book_appointment.

  • Find clients who have not come back Runs: Weekly

    Export clients whose last visit was more than 90 days ago and who have no future appointment. Your agent calls export_clients.

Endpoints

What is the Mangomint API?

Cotlet's Mangomint API exposes 13 endpoints for your own Mangomint account: list locations, list services, list appointments, find client, get client timeline, list waitlist, get report, export clients, add client note, book appointment, reschedule appointment, cancel appointment and book from waitlist. The list_locations endpoint returns your business locations with address and time zone. Each endpoint takes simple JSON inputs like location_id, staff_id or client_id and works both as an MCP tool for agents and as a REST call for scripts.

All endpoints · 13 total

missing one? request an endpoint

  • POST

    list_locations

    read

    Returns every location in your Mangomint account. Use the location_id from each item in the other tools. Most single-location businesses have one item.

    POST /api/v1/mangomint/list_locations

    Input

    No parameters.

    Example response

    {
      "locations": [
        {
          "location_id": "loc_1",
          "name": "Downtown",
          "address": "412 Alder St, Portland, OR",
          "time_zone": "America/Los_Angeles"
        }
      ]
    }
  • POST

    list_services

    read

    Returns the services you can book at a location, grouped by category, with duration, price and the staff members who perform each one. Use the service_id values in book_appointment.

    POST /api/v1/mangomint/list_services

    Input

    Input: list_services
    Parameter Type Description
    location_id string Location ID from list_locations. Default: your main location.

    Example response

    {
      "services": [
        {
          "service_id": "svc_signature_facial",
          "name": "Signature Facial",
          "category": "Facials",
          "duration_minutes": 60,
          "price": {
            "amount": 120,
            "currency": "USD"
          },
          "staff": [
            {
              "staff_id": "st_207",
              "name": "Alex"
            }
          ]
        },
        {
          "service_id": "svc_brow_shape",
          "name": "Brow Shaping",
          "category": "Brows",
          "duration_minutes": 30,
          "price": {
            "amount": 45,
            "currency": "USD"
          },
          "staff": [
            {
              "staff_id": "st_207",
              "name": "Alex"
            },
            {
              "staff_id": "st_311",
              "name": "Sam"
            }
          ]
        }
      ]
    }
  • POST

    list_appointments

    read

    Returns appointments in a date range in start order, each with client, services, staff member, start, end and appointment note. Filter by staff member to read one calendar. Canceled appointments are left out unless include_canceled is true.

    POST /api/v1/mangomint/list_appointments

    Input

    Input: list_appointments
    Parameter Type Description
    location_id string Location ID from list_locations. Default: your main location.
    from required date First day, inclusive.
    to date Last day, inclusive. Default: same as from.
    staff_id string Only this staff member.
    include_canceled boolean Also return canceled and no-show appointments. Default: false.

    Example response

    {
      "appointments": [
        {
          "appointment_id": "ap_903114",
          "client": {
            "client_id": "cl_48213",
            "name": "Jamie Doe"
          },
          "services": [
            {
              "service_id": "svc_signature_facial",
              "name": "Signature Facial"
            }
          ],
          "staff": {
            "staff_id": "st_207",
            "name": "Alex"
          },
          "start": "2026-10-12T14:00:00-07:00",
          "end": "2026-10-12T15:00:00-07:00",
          "status": "booked",
          "note": null
        }
      ]
    }
  • POST

    find_client

    read

    Searches your client list and returns every match with contact details, tags and client notes. Client notes are the internal notes Mangomint shows when you book or check out that client. Pass client_id to the other client tools.

    POST /api/v1/mangomint/find_client

    Input

    Input: find_client
    Parameter Type Description
    query required string Name, email or phone number.

    Example response

    {
      "clients": [
        {
          "client_id": "cl_48213",
          "name": "Jamie Doe",
          "email": "client@example.com",
          "phone": "+15035550142",
          "tags": [
            "VIP"
          ],
          "client_notes": [
            "Prefers fragrance-free products"
          ]
        }
      ]
    }
  • POST

    get_client_timeline

    read

    Returns entries from one client's timeline, newest first: appointments, sales, timeline notes and submitted forms. Use limit to read the latest few visits before a booking.

    POST /api/v1/mangomint/get_client_timeline

    Input

    Input: get_client_timeline
    Parameter Type Description
    client_id required string Client ID from find_client.
    limit integer 1 to 100 entries, newest first. Default: 25.

    Example response

    {
      "client_id": "cl_48213",
      "entries": [
        {
          "type": "appointment",
          "date": "2026-09-14T14:00:00-07:00",
          "summary": "Signature Facial with Alex"
        },
        {
          "type": "sale",
          "date": "2026-09-14T15:05:00-07:00",
          "summary": "Checkout, 1 service, 1 product"
        },
        {
          "type": "timeline_note",
          "date": "2026-09-14T15:10:00-07:00",
          "summary": "Skin was dry; added hydrating serum"
        }
      ]
    }
  • POST

    list_waitlist

    read

    Returns the waitlist entries for one day with the openings Mangomint found for each. Needs the Intelligent Waitlist app enabled and an Admin user or the Can manage waitlist permission. Pass entry_id and opening_id to book_from_waitlist.

    POST /api/v1/mangomint/list_waitlist

    Input

    Input: list_waitlist
    Parameter Type Description
    location_id string Location ID from list_locations. Default: your main location.
    date required date Calendar day to read.

    Example response

    {
      "entries": [
        {
          "entry_id": "wl_2207",
          "client": {
            "client_id": "cl_51007",
            "name": "Priya Shah"
          },
          "service": "Signature Facial",
          "openings": [
            {
              "opening_id": "op_88a1",
              "staff": "Alex",
              "start": "2026-10-13T11:00:00-07:00"
            }
          ]
        }
      ]
    }
  • POST

    get_report

    read

    Returns one of the reports from the Reports app as rows. Sales Summary gives service and product quantities and sales totals for each day; Client Retention gives how many clients from the period visited again within 90 or 180 days. Needs an Admin user or the Can access company reports permission.

    POST /api/v1/mangomint/get_report

    Input

    Input: get_report
    Parameter Type Description
    report required enum sales_summary, service_sales, product_sales, sales_by_time_period, sales_by_staff, canceled_appointments or client_retention.
    from required date First day, inclusive.
    to required date Last day, inclusive.
    location_ids string[] Locations to include. Default: all.

    Example response

    {
      "report": "sales_summary",
      "from": "2026-10-05",
      "to": "2026-10-11",
      "currency": "USD",
      "rows": [
        {
          "date": "2026-10-05",
          "services_qty": 31,
          "services_total": 3120,
          "products_qty": 6,
          "products_total": 214,
          "total": 3334
        },
        {
          "date": "2026-10-06",
          "services_qty": 28,
          "services_total": 2870,
          "products_qty": 4,
          "products_total": 148,
          "total": 3018
        },
        {
          "date": "2026-10-07",
          "services_qty": 35,
          "services_total": 3540,
          "products_qty": 9,
          "products_total": 302,
          "total": 3842
        },
        {
          "date": "2026-10-08",
          "services_qty": 33,
          "services_total": 3315,
          "products_qty": 5,
          "products_total": 176,
          "total": 3491
        },
        {
          "date": "2026-10-09",
          "services_qty": 41,
          "services_total": 4210,
          "products_qty": 12,
          "products_total": 388,
          "total": 4598
        },
        {
          "date": "2026-10-10",
          "services_qty": 47,
          "services_total": 4760,
          "products_qty": 10,
          "products_total": 341,
          "total": 5101
        },
        {
          "date": "2026-10-11",
          "services_qty": 12,
          "services_total": 1180,
          "products_qty": 2,
          "products_total": 64,
          "total": 1244
        }
      ],
      "totals": {
        "services_qty": 227,
        "services_total": 22995,
        "products_qty": 48,
        "products_total": 1633,
        "total": 24628
      }
    }
  • POST

    export_clients

    read

    Applies the filters you give, as the Clients app does, and returns a link to the CSV file. Combine last_visit_days_ago and has_future_appointment to find clients who have not come back. The file has contact details, so open the link yourself.

    POST /api/v1/mangomint/export_clients

    Input

    Input: export_clients
    Parameter Type Description
    last_visit_days_ago integer Only clients whose last appointment was more than this many days ago.
    has_future_appointment boolean Only clients with (true) or without (false) a future appointment.
    tag string Only clients with this tag.

    Example response

    {
      "status": "ready",
      "filters": {
        "last_visit_days_ago": 90,
        "has_future_appointment": false
      },
      "row_count": 42,
      "download_url": "https://files.cotlet.example/exports/mangomint-clients-2026-10-11.csv",
      "expires_at": "2026-10-11T22:00:00+02:00"
    }
  • POST

    add_client_note

    write

    Adds an internal note to a client profile. A client note shows whenever staff book, view or check out that client; a timeline note is a dated entry on the client timeline. Notes are never shown to the client and reach no one, so add_client_note runs without asking first.

    POST /api/v1/mangomint/add_client_note

    Input

    Input: add_client_note
    Parameter Type Description
    client_id required string Client ID from find_client.
    text required string Note text. Internal, never shown to the client.
    kind enum client or timeline. Default: timeline.

    Example response

    {
      "client_id": "cl_48213",
      "kind": "client",
      "status": "added",
      "text": "Allergic to lavender oil"
    }
  • POST

    book_appointment

    write

    Books the services in the order given, back to back, for one client with one staff member at the start time. The staff member must be on the schedule and free for the full length. Returns the appointment with start and end. By default you confirm each call; you can switch that off for this tool.

    POST /api/v1/mangomint/book_appointment

    Input

    Input: book_appointment
    Parameter Type Description
    client_id required string Client ID from find_client.
    location_id string Location ID from list_locations. Default: your main location.
    service_ids required string[] Service IDs from list_services, in order.
    staff_id required string Staff member performing the services.
    start required datetime ISO 8601 with time zone.
    note string Appointment note.

    Example response

    {
      "appointment_id": "ap_903114",
      "status": "booked",
      "client": {
        "client_id": "cl_48213",
        "name": "Jamie Doe"
      },
      "services": [
        {
          "service_id": "svc_signature_facial",
          "name": "Signature Facial",
          "duration_minutes": 60
        }
      ],
      "staff": {
        "staff_id": "st_207",
        "name": "Alex"
      },
      "start": "2026-10-16T14:00:00-07:00",
      "end": "2026-10-16T15:00:00-07:00"
    }
  • POST

    reschedule_appointment

    write

    Moves one appointment to a new start and, if you pass staff_id, to another staff member, as dragging it on the calendar does. Mangomint sends its automated reschedule message only for changes clients make in the client portal, so set notify_client to true to tell the client about this one. By default you confirm each call; you can switch that off for this tool.

    POST /api/v1/mangomint/reschedule_appointment

    Input

    Input: reschedule_appointment
    Parameter Type Description
    appointment_id required string Appointment ID from list_appointments.
    start required datetime New start, ISO 8601 with time zone.
    staff_id string New staff member. Default: unchanged.
    notify_client boolean Send the client a notification about the change. Default: false.

    Example response

    {
      "appointment_id": "ap_903114",
      "status": "rescheduled",
      "staff": {
        "staff_id": "st_207",
        "name": "Alex"
      },
      "start": "2026-10-13T11:00:00-07:00",
      "end": "2026-10-13T12:00:00-07:00",
      "client_notified": true
    }
  • POST

    cancel_appointment

    write

    Cancels one appointment with the cancellation type you choose: normal (the client canceled within the cancellation period), late (after it) or no_show. The client is notified if cancellation notifications are on in Mangomint. A late cancellation or no show does not charge a fee by itself; the fee is added at checkout. By default you confirm each call; you can switch that off for this tool.

    POST /api/v1/mangomint/cancel_appointment

    Input

    Input: cancel_appointment
    Parameter Type Description
    appointment_id required string Appointment ID from list_appointments.
    type required enum normal, late or no_show.

    Example response

    {
      "appointment_id": "ap_903210",
      "status": "canceled",
      "type": "late"
    }
  • POST

    book_from_waitlist

    write

    Accepts one opening for one waitlist entry, the same as Book on the calendar notification, and puts the client on the calendar. Needs an Admin user or the Can manage waitlist permission. By default you confirm each call; you can switch that off for this tool.

    POST /api/v1/mangomint/book_from_waitlist

    Input

    Input: book_from_waitlist
    Parameter Type Description
    entry_id required string Waitlist entry ID from list_waitlist.
    opening_id required string Opening ID from the same entry.

    Example response

    {
      "entry_id": "wl_2207",
      "status": "booked",
      "appointment_id": "ap_903377",
      "client": {
        "client_id": "cl_51007",
        "name": "Priya Shah"
      },
      "staff": {
        "staff_id": "st_207",
        "name": "Alex"
      },
      "start": "2026-10-13T11:00:00-07:00"
    }

Setup

How do I connect Mangomint to Claude Code, Codex or Cursor?

Connecting Mangomint takes three steps: request access, sign in to Mangomint once, then add one MCP server or call the REST API with the same key.

Connect Mangomint over MCP

  1. 1

    Create an account

    Sign up and add Mangomint in the console. Your API key is there too.

  2. 2

    Sign in to Mangomint once

    Open the connect page from the console and sign in to Mangomint the way you always do. We keep the session, never your password, and you can revoke it anytime.

  3. 3

    Add Cotlet to your agent

    Claude Code
    claude mcp add --transport http cotlet \
      https://cotlet.dev/mcp/v1 \
      --header "Authorization: Bearer $COTLET_API_KEY"
    Cursor
    {
      "mcpServers": {
        "cotlet": {
          "url": "https://cotlet.dev/mcp/v1",
          "headers": {
            "Authorization": "Bearer ${COTLET_API_KEY}"
          }
        }
      }
    }
    Codex
    # ~/.codex/config.toml
    [mcp_servers.cotlet]
    url = "https://cotlet.dev/mcp/v1"
    bearer_token_env_var = "COTLET_API_KEY"

    Paste the snippet for your client. The same server and key serve every app you connect, so you do this once.

  4. 4

    Ask your agent

    Prompt

    Alex is out sick today. Move her appointments to tomorrow at the same times, or to another stylist who does the same service today, and tell me which ones didn't fit.

    Ask in plain words. Your agent finds the Mangomint tools on the server and calls them for you; anything that reaches other people waits for your OK unless you switch that off for a tool.

Call Mangomint over REST

  1. 1

    Export your API key

    Shell

    export COTLET_API_KEY="cotlet_..."

    Your scripts use the same API key as your agent. Keep it in an environment variable, never in your code.

  2. 2

    Call a tool

    curl

    curl https://cotlet.dev/api/v1/mangomint/book_appointment \
      -H "Authorization: Bearer $COTLET_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{"client_id":"cl_48213","location_id":"loc_1","service_ids":["svc_signature_facial"],"staff_id":"st_207","start":"2026-10-16T14:00:00-07:00"}'

    Every tool is a POST endpoint at /api/v1/mangomint/{tool}. Send its parameters as JSON, exactly as listed in the endpoints above.

  3. 3

    Read the result

    Example response · book_appointment

    {
      "appointment_id": "ap_903114",
      "status": "booked",
      "client": {
        "client_id": "cl_48213",
        "name": "Jamie Doe"
      },
      "services": [
        {
          "service_id": "svc_signature_facial",
          "name": "Signature Facial",
          "duration_minutes": 60
        }
      ],
      "staff": {
        "staff_id": "st_207",
        "name": "Alex"
      },
      "start": "2026-10-16T14:00:00-07:00",
      "end": "2026-10-16T15:00:00-07:00"
    }

    You get plain JSON back, ready for your script. A failed call costs nothing.

Why Cotlet

Why use Cotlet for Mangomint? Hosted, safe and kept working.

  • Built for agents

    • One MCP server for every app you connect.
    • The same tools as a REST API for scripts and cron jobs.
    • Works with Claude Code, Codex and Cursor.
  • Your login stays yours

    • You sign in to Mangomint yourself. We keep only the session, encrypted with AES-256.
    • The model never sees a login.
    • No stored passwords, no CAPTCHA solving, no MFA bypass.
  • You stay in control

    • Pick read only, or read and write.
    • Anything that reaches other people waits for your OK, unless you switch it off per tool.
    • Revoke access in one click.
  • Kept working for you

    • We test every integration daily.
    • When Mangomint changes, the tool pauses until we fix it.
    • Failed calls cost nothing.

Alternatives

Is there a Mangomint MCP server on GitHub?

No open-source Mangomint MCP server exists. The closest option is Mangomint Webhooks, which send events out to a tool such as Zapier or n8n but cannot read or change anything in Mangomint. Cotlet reads your calendar, clients and reports on demand and can book, move and cancel appointments for you.

Cotlet compared with a Mangomint webhooks
Mangomint webhooks Cotlet
Setup Build a receiving endpoint in your workflow tool, then ask Mangomint chat support to set up the webhook Request access, sign in to Mangomint once, add one MCP server or API key
Reading your data Only events as they happen: appointments, sales, forms, memberships. No lookup of past data Calendar, clients, waitlist and reports on demand
Write actions None: webhooks cannot book, move or cancel Book, reschedule and cancel; each one asks for your OK by default
When Mangomint changes Events keep arriving; anything you built on top stays yours to fix Our team tests it daily and fixes it for you; failed calls are free
Your Mangomint session Not used: events go to your endpoint Encrypted in an EU vault, limited to the actions you allow, revoked in one click
When the session expires Not applicable: webhooks keep sending We keep it alive; if Mangomint logs you out, your agent gets a link to sign in again
Price Set by Mangomint and your workflow tool Free 7-day trial with 5,000 credits, then credits per call

Which one fits you

Pick Cotlet if

  • you are not a developer, or you do not want to maintain a server
  • you need it to keep working when Mangomint changes, without checking it yourself
  • your agent or a script should run it on a schedule, also while your computer is off

Pick an open-source server if

  • you are comfortable installing, updating and fixing it yourself
  • you want the session to stay on your own computer
  • you only need it now and then, from one MCP client

For AI agents

Cotlet for Mangomint in plain text The facts on this page in one block: status, endpoints, access, pricing, contact.

Endpoint health

verified 2h ago

  • list_locations passing
  • list_services passing
  • list_appointments passing
  • find_client passing
  • get_client_timeline passing

+ 8 more endpoints

13/13 passing latest check self-healing

mangomint.txt

Mangomint has no public API and no developer docs (checked 11 Oct 2026). Its Integrations page lists Shopify, Mailchimp, Webhooks, Docovia and Doxy.me; Webhooks only send event data out (appointments, sales, forms, memberships), so nothing can read your calendar on demand or book, move or cancel an appointment.
Cotlet provides a hosted MCP server and REST API for Mangomint: 13 tools (8 read, 5 write).
Access       Request access at https://cotlet.dev/app/signup?app=mangomint; we email the API key.

MCP server   https://cotlet.dev/mcp/v1
REST base    https://cotlet.dev/api/v1/mangomint
Auth         Authorization: Bearer <COTLET_API_KEY>. Listing endpoints and schemas needs no key; calling an endpoint needs one.
Tools        list_locations, list_services, list_appointments, find_client, get_client_timeline, list_waitlist, get_report, export_clients, add_client_note, book_appointment, reschedule_appointment, cancel_appointment, book_from_waitlist
Confirm      book_appointment, reschedule_appointment, cancel_appointment, book_from_waitlist (by default the user approves each call; the user can switch this off per tool, e.g. for scheduled automations)
Markdown     https://cotlet.dev/integrations/mangomint-api-mcp-server.md

How access works:
1. The user requests access at https://cotlet.dev/app/signup?app=mangomint (Mangomint is pre-selected). Each request is reviewed and the API key is sent by email.
2. The user signs in to Mangomint once in a browser. An agent cannot do this step.
3. The API key goes into the MCP client or the REST call as a bearer token.

Fits: people who want a hosted Mangomint server that someone else maintains, including non-developers.

Policy: Cotlet never stores passwords, never solves CAPTCHAs, never bypasses MFA.
Company: legal details in the Terms of service at https://cotlet.dev/terms. Contact contact@cotlet.dev.
Session: the user signs in to Mangomint in a browser; Cotlet keeps only the session, AES-256 encrypted, revocable in the dashboard at any time.
Terms: the user stays responsible for following Mangomint's terms; Cotlet is not affiliated with Mangomint.
Full page as Markdown

Automations

Can Mangomint automations run on a schedule in n8n, Make or Zapier?

Yes. Cotlet does not replace your automation platform: it gives it a Mangomint connection it does not have, with the same API key as your agent. Write actions ask for your OK by default; switch that off in your dashboard for the tools you choose, for example to reschedule appointments when staff is out, and the schedule runs on its own. Cotlet runs in the cloud, so it keeps going while your computer is off.

Where to run Mangomint automations through Cotlet, and how to schedule them
Where How to connect How to schedule
Your AI agent Add https://cotlet.dev/mcp/v1 with your API key. A scheduled agent run, for example a Claude Code routine.
n8n MCP Client node with https://cotlet.dev/mcp/v1, or an HTTP Request node to https://cotlet.dev/api/v1/mangomint/{tool}. Schedule Trigger node.
Make HTTP module: POST https://cotlet.dev/api/v1/mangomint/{tool} with an Authorization: Bearer header and a JSON body. Scenario schedule.
Zapier Webhooks by Zapier: POST https://cotlet.dev/api/v1/mangomint/{tool} with the same header and body. Schedule by Zapier trigger.
Your own script POST https://cotlet.dev/api/v1/mangomint/{tool} with your API key. cron or GitHub Actions.

Pricing & limits

How much does the Mangomint API cost?

Free 7-day trial with 5,000 credits, no card needed. After that, the Mangomint API comes with the Cotlet plan, from $29 a month for 3,000 credits, with no limit on apps. Each month's credits stay valid for 3 months, so unused credits add up.

Cotlet plan sizes: price, monthly credits and price per credit
Size Price Credits / month Per credit
Solo $29/mo 3,000 about $0.0097
Pro $99/mo 12,000 about $0.0083
Agency $299/mo 40,000 $0.0075

Each successful call uses credits for the work it takes; failed calls and timeouts cost nothing. A hard spend cap is on by default. Authenticate with the Authorization: Bearer header.

About Cotlet

How Cotlet holds your access

Cotlet hosts MCP servers and REST APIs for apps with no usable API. Your agent works in your own Mangomint account.

Company details
The legal name, address and registration numbers of the company behind Cotlet are in the Terms of service. Terms
Your session
You sign in to Mangomint yourself, in your browser. We keep only the session, never your password: encrypted with AES-256 in an EU vault, isolated to your account and used only when your agent calls a Mangomint tool you allowed. When it expires, your agent gives you a link to sign in again. Security
Revoking access
Disconnect Mangomint in your dashboard: the session is deleted and access ends at once. Actions that reach other people wait for your OK unless you switch that off per tool.
What we never do
Store passwords, solve CAPTCHAs or bypass MFA.
Mangomint's terms
You use your own Mangomint account and stay responsible for following Mangomint's terms. Cotlet is independent and not affiliated with Mangomint. Terms
Contact
Questions about the company, security or an app: contact@cotlet.dev
About Cotlet

Frequently asked questions

How do I get access?

Request access and pick Mangomint. Cotlet reviews each request and emails you your API key.

Do I need to be technical?

No. You sign in to Mangomint once in your browser and paste one command into your agent, or one URL into n8n. Your agent can walk you through it. There is no server to install, update or fix.

Is a hosted server safe? My Mangomint session would leave my computer.

Cotlet keeps your Mangomint session encrypted with AES-256 in an EU vault, isolated to your account and used only for the tools you allow: read only, or read and write. The AI model never sees it, and you revoke it in one click. A local server keeps the same session in a file on your computer, readable by any program you run, and needs a fresh sign-in whenever it expires.

Do I need a special Mangomint plan or permission?

No special plan: Cotlet works in your own Mangomint account. Some tasks need a permission in Mangomint: reports need an Admin user or Can access company reports, and the waitlist needs an Admin user or Can manage waitlist.

Can my agent post or send messages in Mangomint without asking me?

No. Every call to book_appointment, reschedule_appointment, cancel_appointment or book_from_waitlist waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals. add_client_note runs without asking, because it sends nothing to anyone and one call undoes it.

Can I use the Mangomint API in n8n?

Yes. Add https://cotlet.dev/mcp/v1 with your API key in n8n's MCP Client node, or call https://cotlet.dev/api/v1/mangomint/{tool} from the HTTP Request node.

Give your agent access to Mangomint.

Request access and pick it. We review each request and email you your API key. Free 7-day trial with 5,000 credits, no card needed.