AroFlo MCP Server

Tasks, schedules, quotes and invoices in your AroFlo account.

Hosted MCP Server

npx add-mcp 'https://cotlet.dev/mcp/v1/aroflo'

Installs into Claude Code, Codex, Cursor and more

Documentation

Cotlet · Integrations · How it works · Security · For developers · For automation agencies · Blog · API docs · Help center · Changelog · Contact · Pricing · Sign up

AroFlo API and MCP server

Yes, AroFlo has a REST API (checked 23 Oct 2026), but it is off by default and an account asks AroFlo support to enable it. Each request carries an HMAC-SHA512 signature, replies are XML unless you ask for JSON, and the API is capped at 2,000 calls a day. AroFlo's docs and help centre name no MCP server.

Tasks, schedules, quotes and invoices in your AroFlo account. Use it in ChatGPT, Claude or any AI agent over MCP, or in n8n, Make and scripts over REST.

MCP setup REST API guide

Job management software for trade businesses in Australia and New Zealand: tasks, quotes, scheduling, labour and materials, purchase orders and invoices in one account.

What is the AroFlo API?

Cotlet's AroFlo API exposes 14 endpoints for your own AroFlo account: list tasks, get a task, list clients, list quotes, list invoices, get an invoice, list purchase orders, create a task, schedule a task, update task status, add a task note, create a final invoice, approve an invoice and email an invoice. The list_tasks endpoint returns list tasks from the Open or Closed task list, with filters. Each endpoint takes simple JSON inputs like task_id, cursor or search and works both as an operation of the aroflo_read or aroflo_write MCP tool for agents and as a REST call for scripts.

Yes, AroFlo has a REST API (checked 23 Oct 2026), but it is off by default and an account asks AroFlo support to enable it. Cotlet is a hosted MCP server and REST API for AroFlo with 14 endpoints (7 read, 7 write): you sign in once in your own cloud browser, your AI agent does the work.

Does AroFlo have an official API?

Yes, AroFlo has a REST API (checked 23 Oct 2026), but it is off by default and an account asks AroFlo support to enable it. Each request carries an HMAC-SHA512 signature, replies are XML unless you ask for JSON, and the API is capped at 2,000 calls a day. AroFlo's docs and help centre name no MCP server.

TaskAroFlo officialCotlet
List and read tasksYes: Tasks zone, filtered with WHERE clausesYes
List invoices by statusYes: Invoices zone, for example status = pendingYes
Create or update a taskPartly: POST with signed postxml; per-zone fields sit in the Postman collectionYes
Schedule a technician on a taskPartly: POST with signed postxml; per-zone fields sit in the Postman collectionYes
Create a final invoice from a taskPartly: Invoice queries are documented on the main page; write details sit in the Postman collectionYes
Email an invoice to the clientNo: The help centre documents emailing only as an app actionYes
Work without asking AroFlo support to enable the APINoYes
Run more than 2,000 calls a dayNo: The cap resets at 00:00 Melbourne time; single-ID lookups have a second cap of 20,000Yes

Sources: AroFlo API documentation, AroFlo Help: AroFlo API, AroFlo Help: Invoice Status, AroFlo Help: Schedule a Task or Quote in AroFlo Office

Quick reference

Yes, AroFlo has a REST API (checked 23 Oct 2026), but it is off by default and an account asks AroFlo support to enable it. Each request carries an HMAC-SHA512 signature, replies are XML unless you ask for JSON, and the API is capped at 2,000 calls a day. AroFlo's docs and help centre name no MCP server.
Cotlet provides a hosted MCP server and REST API for AroFlo: 14 tools (7 read, 7 write).
Access       Sign up at https://cotlet.dev/app/signup?app=aroflo and request the app in the Cotlet console. ChatGPT and Claude connect with OAuth at https://cotlet.dev/mcp/v1/connect, no API key; code editors and scripts use an API key from the console.

MCP server   https://cotlet.dev/mcp/v1
MCP tools    aroflo_read, aroflo_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base    https://cotlet.dev/api/v1/aroflo, each operation at its own route, e.g. POST /api/v1/aroflo/clients/{client_id}/tasks
Auth         Authorization: Bearer <COTLET_API_KEY>. Listing endpoints and schemas needs no key; calling an endpoint needs one. Over MCP the input schemas come with sign-in.
Operations   list_tasks, get_task, list_clients, list_quotes, list_invoices, get_invoice, list_purchase_orders, create_task, schedule_task, update_task_status, add_task_note, create_invoice_from_task, approve_invoice, email_invoice
Confirm      create_task, schedule_task, update_task_status, add_task_note, create_invoice_from_task, approve_invoice, email_invoice (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/aroflo-api-mcp-server.md

How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=aroflo and requests AroFlo in the Cotlet console.
2. The user signs in to AroFlo once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables AroFlo for agents. An agent cannot do this step.
3. ChatGPT and Claude: the user adds https://cotlet.dev/mcp/v1/connect as a connector and signs in to Cotlet (OAuth). Code editors and scripts: an API key from the console goes into the MCP client or the REST call as a bearer token.

Fits: people who want a hosted AroFlo server that someone else maintains, including non-developers. Developers who prefer to run and fix code on their own computer can use an open-source AroFlo MCP server instead.

Policy: Cotlet never stores passwords and never bypasses MFA.
Company: legal details in the Terms of service at https://cotlet.dev/terms. Contact contact@cotlet.dev.
Sign-in: the user signs in to AroFlo in their own Cloud Browser, a Chrome Cotlet runs for them in the EU; password saving is off, the profile is AES-256-GCM encrypted, and agents get AroFlo only after the user enables it. Calls are requests from that browser's IP with its cookies, each listed in the user's Background activity. Disable for agents, signing out in the browser or Reset browser cuts access. Cotlet is run by Take Group sp. z o.o. (EU VAT PL6342984273).
API key: holds no AroFlo login or cookies, only asks Cotlet to run a tool. Each key is scoped to chosen apps and tools, read only or read and write. Actions that reach other people wait for the user's approval by default, so a leaked key cannot post or message as the user. Every call is in the activity log; deleting the key ends access at once.
Terms: the user stays responsible for following AroFlo's terms; Cotlet is not affiliated with AroFlo.

What can an AI agent do in AroFlo?

Cotlet is best for AroFlo office staff and trade business owners who want an AI agent to create and schedule tasks and invoice completed jobs without running or fixing a server.

  • Invoice completed jobs (runs: daily): "List AroFlo tasks completed since Monday. Skip any job that already has an invoice, create the final invoice for the rest, and show me the lines. Approve and email only the unquoted ones." → list_tasks, list_invoices, create_invoice_from_task, get_task, get_invoice, approve_invoice, email_invoice
  • Create a job and schedule a technician (runs: daily): "Create an AroFlo task for Harbour Café, aircon not cooling, due Friday, and schedule Sam Rowe on Friday from 9 to 11. Add a note to bring a contactor kit." → list_clients, create_task, schedule_task, get_task
  • Review invoices waiting for approval (runs: daily): "List AroFlo invoices in Pending Approval. Open each one, approve those with at least one line and a total above zero, and list the rest with the reason." → list_invoices, get_invoice, approve_invoice
  • Morning list of open jobs (runs: daily): "Every morning list the open AroFlo tasks due this week by status, and flag the ones with no schedule." → list_tasks, get_task
  • Log updates on a task: "Add a note to AroFlo task J1187 saying the part arrived, and set the task to In Progress." → get_task, add_task_note, update_task_status

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

Yes. Cotlet does not replace your automation platform: it gives it a AroFlo 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 invoice completed jobs, and the schedule runs on its own. Cotlet runs in the cloud, so it keeps going while your computer is off.

WhereHow to connectHow to schedule
Your AI agentAdd https://cotlet.dev/mcp/v1 with your API key.A scheduled agent run, for example a Claude Code routine.
n8nMCP Client node with https://cotlet.dev/mcp/v1, or an HTTP Request node with the endpoint's method and URL, such as GET https://cotlet.dev/api/v1/aroflo/tasks.Schedule Trigger node.
MakeHTTP module: the endpoint's method and URL with an Authorization: Bearer header, and a JSON body for POST, PUT and PATCH.Scenario schedule.
ZapierWebhooks by Zapier, Custom Request: the same method, URL, header and body.Schedule by Zapier trigger.
Your own scriptGET https://cotlet.dev/api/v1/aroflo/tasks with your API key.cron or GitHub Actions.

Tools

For AI agents: Every endpoint and its schema is public. The 14 endpoints on this page, with parameters and example responses, can be listed without an account. Calling one returns 401 without an API key and 403 while the key has no access to AroFlo.

list_tasks

List tasks from the Open or Closed task list, with filters. Access: read. REST: GET /api/v1/aroflo/tasks. MCP: aroflo_read → list_tasks.

ParameterTypeRequiredDescription
viewstringnoOpen or Closed, as under Workflow > Tasks. Defaults to Open.
statusstringnoNot Started, In Progress, Pending or Completed.
clientstringnoClient name to filter by.
searchstringnoText to search for in the task list.
cursorstringnoNext page cursor from the previous call.

Returns one page of tasks with task_id, job number, name, client, location, status, substatus, priority, due date and the person it is assigned to. The order is the one the AroFlo list shows. Substatuses are specific to each business, so the value is whatever your site administrator set up. Follow next_cursor until it is null.

Example response:

{
  "tasks": [
    {
      "task_id": "task_8790",
      "job_number": "J1170",
      "name": "Replace compressor contactor",
      "client": "Harbour Café",
      "location": "12 Wharf Road",
      "status": "Completed",
      "substatus": null,
      "priority": "Normal",
      "due_date": "2026-10-20",
      "assigned_to": "Dana Pike"
    },
    {
      "task_id": "task_8793",
      "job_number": "J1174",
      "name": "Annual fire panel service",
      "client": "Northside Strata",
      "location": "4 Elm Court",
      "status": "Completed",
      "substatus": null,
      "priority": "Normal",
      "due_date": "2026-10-21",
      "assigned_to": "Dana Pike"
    }
  ],
  "next_cursor": null
}

get_task

Read one task with its schedules, notes, quote and invoices. Access: read. REST: GET /api/v1/aroflo/tasks/{task_id}. MCP: aroflo_read → get_task.

ParameterTypeRequiredDescription
task_idstringyesTask ID from list_tasks.

Returns the task header, every schedule with its resources and times, the notes on the Notes tab, the quote behind the task if there is one, and the invoices raised from it. Use it to check what AroFlo holds after a write. A task you cannot open with your user's permission group fails with APP_PERMISSION_DENIED.

Example response:

{
  "task_id": "task_8814",
  "job_number": "J1187",
  "name": "Aircon not cooling",
  "client": "Harbour Café",
  "location": "12 Wharf Road",
  "task_type": "Service Call",
  "status": "Not Started",
  "substatus": null,
  "priority": "High",
  "due_date": "2026-10-30",
  "assigned_to": "Dana Pike",
  "description": "Café split system blowing warm air since Monday.",
  "quote": null,
  "schedules": [
    {
      "schedule_id": "sched_5532",
      "resources": [
        "Sam Rowe"
      ],
      "start": "2026-10-30T09:00",
      "finish": "2026-10-30T11:00"
    }
  ],
  "notes": [
    {
      "note_id": "note_771",
      "text": "Bring a contactor kit",
      "sticky": false,
      "created_by": "Dana Pike"
    }
  ],
  "invoices": []
}

list_clients

Search clients by name. Access: read. REST: GET /api/v1/aroflo/clients. MCP: aroflo_read → list_clients.

ParameterTypeRequiredDescription
searchstringnoPart of the client name.
cursorstringnoNext page cursor from the previous call.

Returns clients with client_id, name and their locations. Use the client_id in create_task. A search with no match returns an empty list and no error. Cotlet has no tool that creates a client, because AroFlo asks for an extra permission for that.

Example response:

{
  "clients": [
    {
      "client_id": "client_311",
      "name": "Harbour Café",
      "locations": [
        "12 Wharf Road"
      ]
    }
  ],
  "next_cursor": null
}

list_quotes

List quotes from the Quotes List. Access: read. REST: GET /api/v1/aroflo/quotes. MCP: aroflo_read → list_quotes.

ParameterTypeRequiredDescription
clientstringnoClient name to filter by.
searchstringnoText to search for in the Quotes List.
cursorstringnoNext page cursor from the previous call.

Returns one page of quotes with quote_id, quote name, client, estimator and due date. Quotes are read only here: creating or sending one is not a tool. Follow next_cursor until it is null.

Example response:

{
  "quotes": [
    {
      "quote_id": "quote_2210",
      "name": "Fire panel replacement",
      "client": "Northside Strata",
      "estimator": "Dana Pike",
      "due_date": "2026-11-06"
    }
  ],
  "next_cursor": null
}

list_invoices

List invoices from the Invoices List by status. Access: read. REST: GET /api/v1/aroflo/invoices. MCP: aroflo_read → list_invoices.

ParameterTypeRequiredDescription
statusstringnoIn Progress, Pending Approval, Approved or Processed.
unpaid_onlybooleannoSame as the Unpaid filter on the Invoices List.
searchstringnoInvoice No, Task Ref, Job Number, Cust. Order No or client name.
business_unitsstringnoThis Business Unit Only, Include Child Business Units or Include All Business Units.
fromstringnoStart date, YYYY-MM-DD. Used with status Processed.
tostringnoEnd date, YYYY-MM-DD. Used with status Processed.
cursorstringnoNext page cursor from the previous call.

Returns one page of invoices with invoice_id, invoice number, client, job number, status, date and total. The two wider business unit options add the owner to each row. Approved invoices are the ones ready for your accounting package. Follow next_cursor until it is null.

Example response:

{
  "invoices": [
    {
      "invoice_id": "inv_2041",
      "invoice_no": "2041",
      "client": "Harbour Café",
      "job_number": "J1170",
      "status": "Pending Approval",
      "date": "2026-10-21",
      "total": 840
    },
    {
      "invoice_id": "inv_2043",
      "invoice_no": "2043",
      "client": "Northside Strata",
      "job_number": "J1174",
      "status": "Pending Approval",
      "date": "2026-10-22",
      "total": 2150
    },
    {
      "invoice_id": "inv_2044",
      "invoice_no": "2044",
      "client": "Kemp Plumbing Supply",
      "job_number": "J1179",
      "status": "Pending Approval",
      "date": "2026-10-22",
      "total": 460
    }
  ],
  "next_cursor": null
}

get_invoice

Read one invoice with its lines. Access: read. REST: GET /api/v1/aroflo/invoices/{invoice_id}. MCP: aroflo_read → get_invoice.

ParameterTypeRequiredDescription
invoice_idstringyesInvoice ID from list_invoices.

Returns the invoice header, its status and every line with description, quantity, rate and amount. The total is the sum of the lines. Use it to check an invoice before approve_invoice, because an Approved invoice cannot be edited.

Example response:

{
  "invoice_id": "inv_2041",
  "invoice_no": "2041",
  "client": "Harbour Café",
  "job_number": "J1170",
  "status": "In Progress",
  "lines": [
    {
      "description": "Labour",
      "quantity": 3,
      "rate": 120,
      "amount": 360
    },
    {
      "description": "Compressor contactor",
      "quantity": 1,
      "rate": 480,
      "amount": 480
    }
  ],
  "total": 840
}

list_purchase_orders

List purchase orders, for one task or for all. Access: read. REST: GET /api/v1/aroflo/purchase-orders. MCP: aroflo_read → list_purchase_orders.

ParameterTypeRequiredDescription
task_idstringnoOnly the purchase orders of this task.
supplierstringnoSupplier name to filter by.
cursorstringnoNext page cursor from the previous call.

Returns purchase orders with purchase_order_id, supplier, the date and time it must be delivered by and the task it belongs to. Purchase orders are read only here. Follow next_cursor until it is null.

Example response:

{
  "purchase_orders": [
    {
      "purchase_order_id": "po_1530",
      "supplier": "Coastline Refrigeration Supplies",
      "delivery_by": "2026-10-28T10:00",
      "task_id": "task_8814"
    }
  ],
  "next_cursor": null
}

create_task

Create a task for a client in AroFlo. Access: write, asks the user first. REST: POST /api/v1/aroflo/clients/{client_id}/tasks. MCP: aroflo_write → create_task.

ParameterTypeRequiredDescription
client_idstringyesClient ID from list_clients.
task_namestringyesName of the task.
task_typestringyesA Task Type that exists on your site.
descriptionstringnoWhat needs doing.
prioritystringnoA Priority that exists on your site.
due_datestringnoDue date, YYYY-MM-DD.
locationstringnoA location of the client from list_clients.
assign_tostringnoName of the user the task is assigned to.
reported_bystringnoContact who reported the job.

Creates the task as Not Started and returns its task_id and job number. Assign To makes a person responsible for the task but does not book them; use schedule_task for the person who does the work. A task type or priority your site does not have fails with an error that lists the valid ones. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "task_id": "task_8814",
  "job_number": "J1187",
  "status": "Not Started",
  "client": "Harbour Café",
  "assigned_to": "Dana Pike"
}

schedule_task

Book one or more people on a task for a time slot. Access: write, asks the user first. REST: POST /api/v1/aroflo/tasks/{task_id}/schedule. MCP: aroflo_write → schedule_task.

ParameterTypeRequiredDescription
task_idstringyesTask ID from list_tasks.
resourcesstring[]yesNames of the users to schedule.
startstringyesStart, YYYY-MM-DDTHH:MM, local time.
finishstringnoFinish, YYYY-MM-DDTHH:MM, local time.
notestringnoNote for the schedule.

Adds one schedule to the task with each resource and the times, and returns its schedule_id. It does not check availability or clashes. The people you schedule are the ones who do the work, which is different from the person the task is assigned to. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "task_id": "task_8814",
  "job_number": "J1187",
  "schedule_id": "sched_5532",
  "resources": [
    "Sam Rowe"
  ],
  "start": "2026-10-30T09:00",
  "finish": "2026-10-30T11:00",
  "task_status": "Not Started"
}

update_task_status

Set the status and substatus of a task. Access: write, asks the user first. REST: PATCH /api/v1/aroflo/tasks/{task_id}/status. MCP: aroflo_write → update_task_status.

ParameterTypeRequiredDescription
task_idstringyesTask ID from list_tasks.
statusstringyesNot Started, In Progress, Pending or Completed.
substatusstringnoA substatus your site administrator set up.

Changes the status and returns the old and the new value. Completed means the work is done and ready for invoicing or archiving. Another call with the old status undoes it. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "task_id": "task_8814",
  "job_number": "J1187",
  "previous_status": "Not Started",
  "status": "In Progress",
  "substatus": null
}

add_task_note

Add a text note to the Notes tab of a task. Access: write, asks the user first. REST: POST /api/v1/aroflo/tasks/{task_id}/note. MCP: aroflo_write → add_task_note.

ParameterTypeRequiredDescription
task_idstringyesTask ID from list_tasks.
notestringyesNote text.
stickybooleannoKeep the note at the top of the list.

Adds a plain text note and returns its note_id. Who can see the note follows your AroFlo note settings for permission groups and visibility. Cotlet does not change or delete notes afterwards. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "task_id": "task_8814",
  "note_id": "note_772",
  "sticky": false
}

create_invoice_from_task

Create the final invoice of a completed task. Access: write, asks the user first. REST: POST /api/v1/aroflo/tasks/{task_id}/invoice-from-tasks. MCP: aroflo_write → create_invoice_from_task.

ParameterTypeRequiredDescription
task_idstringyesTask ID from list_tasks.

Does what Create Final Invoice does at the bottom of the worksheet and returns the invoice_id and its status. For an unquoted job AroFlo adds the labour and material from the job sheet. The task must be Completed; any other status fails with an error. The invoice is not approved or sent. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "invoice_id": "inv_2041",
  "invoice_no": "2041",
  "task_id": "task_8790",
  "job_number": "J1170",
  "status": "In Progress",
  "total": 840
}

approve_invoice

Set an invoice to Approved and save it. Access: write, asks the user first. REST: POST /api/v1/aroflo/invoices/{invoice_id}/approve. MCP: aroflo_write → approve_invoice.

ParameterTypeRequiredDescription
invoice_idstringyesInvoice ID from list_invoices.

Sets Status to Approved and saves, then returns the invoice. An Approved invoice cannot be changed in AroFlo until its status is set back, and it must be Approved before it can be pushed to your accounting package. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "invoice_id": "inv_2041",
  "invoice_no": "2041",
  "status": "Approved",
  "total": 840
}

email_invoice

Email an invoice to a client as a PDF or a link. Access: write, asks the user first. REST: POST /api/v1/aroflo/invoices/{invoice_id}/email. MCP: aroflo_write → email_invoice.

ParameterTypeRequiredDescription
invoice_idstringyesInvoice ID from list_invoices.
tostringyesRecipient email address.
formatstringnopdf attaches the invoice, link adds a link to view it online. Defaults to pdf.
messagestringnoText above the invoice in the email.

Sends the email from your AroFlo account and returns who it went to and when. The invoice is saved first, because AroFlo needs a saved invoice to email. It usually follows approve_invoice. A sent email cannot be recalled. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "invoice_id": "inv_2041",
  "invoice_no": "2041",
  "status": "Approved",
  "sent_to": "accounts@harborcafe.example",
  "format": "pdf",
  "sent_at": "2026-10-23T09:12:00+11:00"
}

How do I connect AroFlo to ChatGPT, Claude, Cursor or Codex?

Connecting AroFlo takes three steps: sign up, sign in to AroFlo once in your Cloud Browser and enable it for agents, then add Cotlet to ChatGPT or Claude as a connector, with no API key, or add one MCP server or call the REST API with an API key.

Connect AroFlo to your agent.

  1. Create an account Sign up and add AroFlo in the console. ChatGPT and Claude need no API key: you sign in to Cotlet when you add the connector. Code editors and scripts take an API key from the console.

  2. Sign in to AroFlo in your Cloud Browser Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to AroFlo there yourself, the way you always do, then press Enable for agents, read only or read and write. We never save your password, and your agent keeps working even when your computer is off.

  3. Add Cotlet to ChatGPT, Claude or your agent Paste the snippet for your client. The same server and key serve every app you connect, so you do this once.

    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:

{
  "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"
  1. Ask your agent Ask in plain words. Your agent finds the AroFlo 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.
List AroFlo tasks completed since Monday. Skip any job that already has an invoice, create the final invoice for the rest, and show me the lines. Approve and email only the unquoted ones.

Call AroFlo from your scripts.

  1. Export your API key Your scripts use the same API key as your agent. Keep it in an environment variable, never in your code.
export COTLET_API_KEY="cotlet_..."
  1. Call a tool Every tool is an endpoint under /api/v1/aroflo with its own method and path, listed with the endpoints above. Path parameters go in the URL; the other parameters go in the query for GET and DELETE and in a JSON body otherwise.
curl -X POST https://cotlet.dev/api/v1/aroflo/clients/client_311/tasks \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"task_name":"Aircon not cooling","task_type":"Service Call","description":"Café split system blowing warm air since Monday.","priority":"High","due_date":"2026-10-30","assign_to":"Dana Pike"}'
  1. Read the result You get plain JSON back, ready for your script. A failed call costs nothing.
{
  "task_id": "task_8814",
  "job_number": "J1187",
  "status": "Not Started",
  "client": "Harbour Café",
  "assigned_to": "Dana Pike"
}

How to use the AroFlo REST API

Create your Cotlet API key

Create a Cotlet API key with access to AroFlo and its read operations. Store it as COTLET_API_KEY in your environment or automation platform's credential store.

Connect AroFlo in Cotlet and enable it for agents. Account access: Your own AroFlo Office login; what your agent can reach follows your user's permission group.

Make your first AroFlo API request

REST:

curl https://cotlet.dev/api/v1/aroflo/tasks \
  -H "Authorization: Bearer $COTLET_API_KEY"

Read tasks and apply the operation limits

A successful REST call puts the tool output in result. This illustrative response excerpt omits call IDs, messages and credit details.

Illustrative response excerpt:

{
  "status": "success",
  "app": "aroflo",
  "tool": "list_tasks",
  "result": {
    "tasks": [
      {
        "task_id": "task_8790",
        "job_number": "J1170",
        "name": "Replace compressor contactor",
        "client": "Harbour Café",
        "location": "12 Wharf Road",
        "status": "Completed",
        "substatus": null,
        "priority": "Normal",
        "due_date": "2026-10-20",
        "assigned_to": "Dana Pike"
      },
      {
        "task_id": "task_8793",
        "job_number": "J1174",
        "name": "Annual fire panel service",
        "client": "Northside Strata",
        "location": "4 Elm Court",
        "status": "Completed",
        "substatus": null,
        "priority": "Normal",
        "due_date": "2026-10-21",
        "assigned_to": "Dana Pike"
      }
    ],
    "next_cursor": null
  }
}

Returns one page of tasks with task_id, job number, name, client, location, status, substatus, priority, due date and the person it is assigned to. The order is the one the AroFlo list shows.

Substatuses are specific to each business, so the value is whatever your site administrator set up. Follow next_cursor until it is null.

cursor: Next page cursor from the previous call.

Keep the same selection when continuing a list. Compare changed record values as well as identifiers when refreshing your destination.

AroFlo workflows for agents and automations

ToolConnect throughExample workflow
n8nHTTP RequestRead one task with its schedules, notes, quote and invoices. Use get_task in your configured business report.
MakeHTTP > Make a requestList invoices from the Invoices List by status. Use list_invoices in your configured business report.
Python or Node.jsREST APIRead one invoice with its lines. Use get_invoice in your configured business report.

Send Authorization: Bearer <your Cotlet API key> in request headers. You configure the schedule, destination and record comparisons.

Cotlet reads AroFlo; your workflow steps write to your chosen destination. These HTTP workflows do not require a native Cotlet connector or a prebuilt template.

Python and Node.js can use the same HTTP requests without an AI agent. Keep access keys in credentials, outside shared workflow exports.

The API and MCP reference lists operations and inputs. The REST API guide explains authentication, errors and approvals.

Why use Cotlet for AroFlo?

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 ChatGPT, Claude, Claude Code, Codex and Cursor.

Your login stays yours

  • You sign in to AroFlo yourself, in your own Cloud Browser. We never save your password; the profile is encrypted with AES-256-GCM, the cipher 1Password uses.
  • A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory.
  • The model never sees a login.
  • No stored passwords, no MFA bypass.

You stay in control

  • Scope each API key: its apps, its tools, read only or read and write.
  • Anything that reaches other people waits for your OK, so a leaked key cannot post or message as you.
  • Every background request listed in your Background activity. Disable for agents in one click.

Kept working for you

  • We test every integration every 6 hours.
  • When AroFlo changes, the tool pauses until we fix it.
  • Failed calls cost nothing.

Is it safe to connect AroFlo to Cotlet?

Yes. You sign in to AroFlo yourself, in your own Cloud Browser, and we never save your password. Your agents only get AroFlo once you enable it, and every background request is listed. The browser profile is stored encrypted with AES-256-GCM, the same cipher 1Password uses for its vaults and Apple for iCloud Keychain. Independent public scanners grade cotlet.dev A+ and find it clean; click a result to rerun it yourself.

  • A+ on Qualys SSL Labs: Encryption in transit: TLS setup and certificates, on all four server addresses. Live result
  • A+ on securityheaders.com: Browser protections sent with every page, all six headers present. Live result
  • A+ on Mozilla Observatory: Mozilla's web security baseline: score 120 of 100, 12 of 12 tests passed. Live result
  • Clean on Sucuri SiteCheck: No malware, spam or defacement, and not on any of 9 blocklists, Google Safe Browsing included. Live result

How Cotlet protects your access

Common concerns

Who runs Cotlet?

Cotlet is run by Take Group, a Polish software company working since 2019. Take Group runs about 3,200 websites on its own systems and has its own DevOps team for infrastructure security. We built and used integrations like this inside the company for years before opening them as Cotlet.

Is this an official AroFlo integration?

No, Cotlet is independent of AroFlo. AroFlo's own API is too limited for this work. Cotlet works through your own AroFlo account, the way you use AroFlo in the browser, so you need no partner approval and no developer setup.

What about client data and GDPR?

Cotlet is run from the EU and follows the GDPR. Cloud Browsers run in Finland, a Tier 1 country in the ITU Global Cybersecurity Index 2024. Data passes through a call and is not kept after it.

Can I start with read only?

Yes. Enable the app for agents as read only, or make the API key read only, and anything that reaches other people waits for your OK unless you switch that off per tool.

Is it reliable?

Every Cotlet service is checked every 3 minutes from Europe, North America, Asia and Australia. The live results and any outage are public at status.cotlet.dev.

How do I stop?

Press Disable for agents next to AroFlo in your console: your agents lose access at once and you stay signed in. Signing out of AroFlo in the browser works too, and Reset browser deletes the whole profile.

Is there a AroFlo MCP server on GitHub?

Yes. A community AroFlo MCP server exists on GitHub, maintained by one person. It calls the official API, so you ask AroFlo support to enable the API, generate a secret key, host the server yourself and fix it when something changes. Cotlet hosts the same kind of server for you, signs in as you, and our team keeps it working.

GitHub MCP serverCotlet
SetupAsk AroFlo support to enable the API, generate a secret key, install the server and set four credentials as environment variablesSign up, sign in to AroFlo once, add one MCP server or API key
When AroFlo changesIt breaks until you or the maintainer fix itOur team tests it daily and fixes it for you; failed calls are free
Your AroFlo accessAPI secret key and encoded login values in a file on your computer; a new key breaks every integration on the old oneYour session lives in your own Cloud Browser in the EU, profile encrypted, only for the apps you enable, disabled for agents in one click
Daily limitShares AroFlo's cap of 2,000 API calls a day with every other integrationWorks in your signed-in session, so the API cap does not apply
UpkeepYou update, monitor and debug it yourselfNothing to host or update
Where it runsYour computer, while it is onHosted: Claude Code, Codex, Cursor, n8n, Make, Zapier and scripts, also on a schedule
PriceFree, paid for with your timeFree 7-day trial, then pay-as-you-go credit packs, no subscription

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 AroFlo 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 your sign-in to stay on your own computer
  • you only need it now and then, from one MCP client

How much does the AroFlo API cost?

Free 7-day trial with 2,000 credits, no card needed. After that, the AroFlo API is pay as you go with no limit on apps: Credit packs from $29 for 5,000 credits, one-time, no subscription. A successful call uses 10 to 100 credits (10 for most tools, about $0.04 to $0.06), your Cloud Browser uses 50 credits a day while it has an app enabled for agents, however many apps that is, and an agent driving the browser itself uses 5 credits a minute. Credit packs stay valid for 12 months and stack, so unused credits carry over.

CreditsPrice, one timeCalls at 10 creditsPer 1,000 credits
5,000$29500$5.80
15,000$791,500$5.27
32,000$1493,200$4.66
60,000$2496,000$4.15

Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the Authorization: Bearer header. See full pricing

How Cotlet holds your access

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

  • Company details: Cotlet is run by Take Group sp. z o.o., a company registered in Poland. Its full address and registration numbers are in the Terms of service. Terms of service
  • Your sign-in: You sign in to AroFlo yourself, in your own Cloud Browser: a Chrome we run for you in the EU, one per app. We never save your password (password saving is off), the profile is stored encrypted with AES-256-GCM, and your agents get AroFlo only after you enable it. When AroFlo signs you out, your agent gives you a link to sign in again. Security
  • Revoking access: Press Disable for agents next to AroFlo, sign out of AroFlo in your Cloud Browser, or reset the browser. Every background request is listed in your Background activity. Actions that reach other people wait for your OK unless you switch that off per tool.
  • What we never do: Store passwords or bypass MFA.
  • AroFlo's terms: You use your own AroFlo account and stay responsible for following AroFlo's terms. Cotlet is independent and not affiliated with AroFlo. Terms
  • Contact: Questions about the company, security or an app: contact@cotlet.dev

Also listed on: Odel, mcpbeat

AroFlo API and MCP: questions

How do I get access?

Sign up free, open AroFlo in the console and press Activate. Then you create your API key and connect AroFlo there.

Do I need to be technical?

No. You sign in to AroFlo once in your Cloud Browser, a normal Chrome you open from the console, 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 it safe to connect AroFlo to Cotlet?

Yes. You sign in to AroFlo yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get AroFlo once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security.

Is a hosted server safer than a local one? My AroFlo sign-in would leave my computer.

On Cotlet you sign in inside your own Cloud Browser, which only you open, and its profile is stored encrypted with AES-256-GCM in the EU. Agents get only the apps you enable, and every background request is listed. A local server keeps your AroFlo cookie in a plain file on your computer, readable by any program you run, and stops when your computer is off.

Why does Cotlet send requests instead of clicking in my browser?

To be fast, Cotlet doesn't click through AroFlo's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. AroFlo sees the same browser and IP you signed in with, and every request is listed in your Background activity.

What if someone gets my Cotlet API key?

The key holds no AroFlo login or cookies, it only asks Cotlet to run a tool. It can call only the apps and tools you gave it, and a read-only key changes nothing. Anything that reaches other people, like posts, comments or messages, waits for your OK in the dashboard by default, so a leaked key cannot post or message as you. When you switch approval off for a scheduled job, give that job its own key limited to that one tool. Every call is in your activity log, and deleting the key ends access at once.

Why a signed-in browser and not OAuth, like other integration platforms?

AroFlo offers no OAuth token you can simply grant for these tools: its official API leaves them out or needs a developer app, a plan or an approval first (see the official API section above). That is why Cotlet sets the limits itself: per key, per tool, with your approval before anything reaches other people. Cotlet is run by Take Group sp. z o.o., an EU company (VAT PL6342984273).

How do I connect AroFlo to ChatGPT or Claude?

Sign up at cotlet.dev, log in to AroFlo 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 AroFlo account through Cotlet, in their phone apps too.

What can ChatGPT do in AroFlo?

With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in AroFlo: invoice completed jobs; create a job and schedule a technician; review invoices waiting for approval. You ask in plain words, and anything that reaches other people waits for your OK first.

Is there an official ChatGPT or Claude app for AroFlo?

No. AroFlo has no ChatGPT or Claude connector of its own (checked 8 Nov 2026). Cotlet is an independent one that works in ChatGPT, Claude, Cursor and any MCP client, on your signed-in account.

Can ChatGPT create a job and schedule a technician in AroFlo?

Yes, with Cotlet. ChatGPT creates the task for the client, books the technician with schedule_task and adds task notes in your AroFlo account. Each change waits for your OK by default, which you can switch off per tool.

Can ChatGPT send an invoice in AroFlo?

Yes, with Cotlet. ChatGPT creates the final invoice from a completed task, approves it and emails it to the client from your AroFlo account. Sending waits for your OK by default.

Do I need AroFlo to switch on API access for Cotlet?

No. Cotlet works in your signed-in AroFlo Office session, not through the API. AroFlo keeps API access off until you ask its support, and then caps it at 2,000 calls a day, so Cotlet calls do not count against that cap. Your own login and permission group still decide what the agent can open.

Which AroFlo user does my agent need?

Your own Office login. AroFlo permission groups decide which tasks, invoices and notes you can open, and a call outside them fails with APP_PERMISSION_DENIED. Creating a client needs an extra AroFlo permission, and Cotlet has no tool for it, so tasks are created for clients that already exist.

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

No. Every call to create_task, schedule_task, update_task_status, add_task_note, create_invoice_from_task, approve_invoice or email_invoice waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals.

Can I use the AroFlo API in n8n?

Yes. Add https://cotlet.dev/mcp/v1 with your API key in n8n's MCP Client node, or call its endpoints under https://cotlet.dev/api/v1/aroflo from the HTTP Request node.

Can I use the AroFlo API without an AI agent?

Yes. Call Cotlet's REST API from a script or an HTTP step in n8n, Make or Zapier with your Cotlet key. MCP is the alternative for AI agents; you do not need to connect an agent to use REST.


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.