Trengo MCP Server

Sortiere, kennzeichne und beantworte Trengo-Konversationen mit deinem Agenten und schließe sie.

Gehosteter MCP-Server

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

Installiert in Claude Code, Codex, Cursor und mehr

Dokumentation

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

Trengo API and MCP server

Trengo has a REST API for conversations, messages, contacts, labels, WhatsApp templates and reporting, but no official MCP server (checked 20 Oct 2026). The API needs a personal access token and allows 120 requests per minute. Trengo's feature board lists an MCP server request with the status Building and no date.

Triage, label, reply to and close Trengo conversations with your agent. Use it in ChatGPT, Claude or any AI agent over MCP, or in n8n, Make and scripts over REST.

MCP setup REST API guide

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by Trengo. Trengo is a trademark of its owner. If Trengo's own integrations cover what you need, use them first.

Customer inbox for email, WhatsApp, Instagram, Facebook, live chat and SMS in one shared place, with labels, rules and quick replies.

What is the Trengo API?

Cotlet's Trengo API exposes 13 endpoints for your own Trengo account: list conversations, search conversations, get conversation, list labels, list users and teams, list quick replies, add label, remove label, set reminder, add internal note, assign conversation, reply to conversation and close conversation. The list_conversations endpoint returns conversations in an inbox folder, with channel, labels, assignee and the last message. Each endpoint takes simple JSON inputs like conversation_id, label or cursor and works both as an operation of the trengo_read or trengo_write MCP tool for agents and as a REST call for scripts.

  • Category: Customer support
  • Endpoints: 13 (6 read, 7 write)
  • Updated: 2026-11-20

Trengo has a REST API for conversations, messages, contacts, labels, WhatsApp templates and reporting, but no official MCP server (checked 20 Oct 2026). Cotlet is a hosted MCP server and REST API for Trengo with 13 endpoints (6 read, 7 write): you sign in once in your own cloud browser, your AI agent does the work.

Does Trengo have an official API?

Trengo has a REST API for conversations, messages, contacts, labels, WhatsApp templates and reporting, but no official MCP server (checked 20 Oct 2026). The API needs a personal access token and allows 120 requests per minute. Trengo's feature board lists an MCP server request with the status Building and no date.

TaskTrengo officialCotlet
List and filter conversationsYes: REST API, filters by status, label, user, channel and contact; no MCP server for agentsYes
Read the messages of a conversationYes: REST APIYes
Reply to a customerYes: REST API, send a ticket message; WhatsApp needs a template to start a conversationYes
Add an internal noteYes: REST API, internal_note flag on a ticket messageYes
Assign to a user or a teamYes: REST APIYes
Close a conversationYes: REST APIYes
Add or remove a labelPartly: The reference lists, creates and detaches labels; an attach call is not in itYes
Quick replies and ticket remindersNo: Neither is in the API referenceYes

Sources: Trengo API: Making requests, Trengo API reference: List all tickets, Trengo feature board: MCP server integration for AI, Trengo Help: Integrating Zapier with Trengo

Quick reference

Trengo has a REST API for conversations, messages, contacts, labels, WhatsApp templates and reporting, but no official MCP server (checked 20 Oct 2026). The API needs a personal access token and allows 120 requests per minute. Trengo's feature board lists an MCP server request with the status Building and no date.
Cotlet provides a hosted MCP server and REST API for Trengo: 13 tools (6 read, 7 write).
Access       Sign up at https://cotlet.dev/app/signup?app=trengo 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    trengo_read, trengo_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base    https://cotlet.dev/api/v1/trengo, each operation at its own route, e.g. POST /api/v1/trengo/conversations/{conversation_id}/assign
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_conversations, search_conversations, get_conversation, list_labels, list_assignees, list_quick_replies, add_label, remove_label, set_reminder, add_internal_note, assign_conversation, reply_to_conversation, close_conversation
Confirm      add_internal_note, assign_conversation, reply_to_conversation, close_conversation (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/trengo-api-mcp-server.md

How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=trengo and requests Trengo in the Cotlet console.
2. The user signs in to Trengo once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Trengo 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 Trengo server that someone else maintains, including non-developers.

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 Trengo 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 Trengo 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 Trengo 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 Trengo's terms; Cotlet is not affiliated with Trengo.

What can an AI agent do in Trengo?

Cotlet is best for support leads on Trengo who want their own AI agent to triage, label, answer and close conversations without running or fixing a server.

  • Triage new conversations (runs: daily): "Go through the new Trengo conversations. Label each one by topic (Billing, Delivery or Bug), assign Billing to the Billing team, Delivery to Sam and Bug to the Tech team, and leave an internal note with the reason. Leave unclear ones for me." → list_labels, list_assignees, list_conversations, get_conversation, add_label, assign_conversation, add_internal_note
  • Reply to waiting customers (runs: daily): "Find my Trengo conversations where the customer wrote last. Reply from my quick replies in my tone, skip anything about refunds or chargebacks and leave an internal note saying why. Send nothing without my OK." → list_conversations, get_conversation, list_quick_replies, reply_to_conversation, add_internal_note
  • Close resolved conversations (runs: weekly): "Every Friday, go through my Trengo conversations where our team wrote last more than 3 days ago. Close the ones where the customer confirmed it worked, set a reminder for Monday 9:00 on the ones still waiting for the customer, and skip any with a note to wait." → list_conversations, get_conversation, set_reminder, close_conversation
  • Daily inbox digest (runs: daily): "Every morning, list the new Trengo conversations and the ones assigned to me where the customer wrote last, grouped by label, with the oldest first." → list_conversations, list_labels
  • Find a customer's earlier conversations: "Search Trengo for lena@example.com and summarize what we told her in her last three conversations before I reply." → search_conversations, get_conversation

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

Yes. Cotlet does not replace your automation platform: it gives it a Trengo 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 triage new conversations, 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/trengo/labels.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/trengo/labels with your API key.cron or GitHub Actions.

Tools

For AI agents: Every endpoint and its schema is public. The 13 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 Trengo.

list_conversations

Conversations in an inbox folder, with channel, labels, assignee and the last message. Access: read. REST: GET /api/v1/trengo/conversations. MCP: trengo_read → list_conversations.

ParameterTypeRequiredDescription
folderenumnonew, assigned_to_me, following or reminders. Default: new.
labelstringnoOnly conversations with this label, by name from list_labels.
last_message_fromenumnocustomer or team. Default: both.
cursorstringnoNext page cursor from the previous call.

Returns the conversations of one folder of the inbox, newest first. Each row has the subject, the contact, the channel, the labels, the assignee and a preview of the last message with who wrote it and when. last_message_from filters each page you read; pass next_cursor back as cursor until it is null. Use get_conversation for the full thread.

Example response:

{
  "conversations": [
    {
      "conversation_id": 5120344,
      "subject": "Invoice shows the wrong VAT number",
      "contact": "Lena Vos",
      "channel": "Email",
      "labels": [],
      "assigned_to": null,
      "last_message": {
        "from": "customer",
        "preview": "Hi, the invoice for order 4471 has the old VAT number on it. Can you send a corrected one?",
        "at": "2026-10-20T06:52:00Z"
      }
    }
  ],
  "next_cursor": null
}

search_conversations

Conversations that match a ticket number, name, phone number, email address or keywords. Access: read. REST: GET /api/v1/trengo/conversations/search. MCP: trengo_read → search_conversations.

ParameterTypeRequiredDescription
querystringyesTicket number, name, phone number with country code, email address, domain or keywords.
fieldenumnosubject, ticket_number or contact_email. Default: all fields.
exactbooleannoOnly match the words in that exact order. Default: false.
cursorstringnoNext page cursor from the previous call.

Runs the inbox search and returns matches in the same shape as list_conversations. The query takes a ticket number, a contact name, a phone number, an email address, a whole email domain such as @example.com, or words from the conversation. Put a phrase in quotation marks, or set exact, to match the words in that order. Deleted tickets do not appear. Pass next_cursor back as cursor for the next page.

Example response:

{
  "conversations": [
    {
      "conversation_id": 5119870,
      "subject": "Where is my parcel?",
      "contact": "Lena Vos",
      "channel": "WhatsApp",
      "labels": [
        "Delivery"
      ],
      "assigned_to": "Sam de Boer",
      "last_message": {
        "from": "team",
        "preview": "It left our warehouse on Monday and arrives tomorrow.",
        "at": "2026-10-14T13:20:00Z"
      }
    }
  ],
  "next_cursor": null
}

get_conversation

One conversation with its contact, labels, assignee and every message, internal notes included. Access: read. REST: GET /api/v1/trengo/conversations/{conversation_id}. MCP: trengo_read → get_conversation.

ParameterTypeRequiredDescription
conversation_idintegeryesConversation ID from list_conversations or search_conversations.

Returns the messages oldest first, each marked from customer, team or note, with the author, the text and the time. Internal notes are included so the agent sees what colleagues wrote. Attachments are not returned. Email bodies come back as plain text.

Example response:

{
  "conversation_id": 5120344,
  "subject": "Invoice shows the wrong VAT number",
  "contact": {
    "name": "Lena Vos",
    "email": "lena@example.com"
  },
  "channel": "Email",
  "labels": [],
  "assigned_to": null,
  "reminder_at": null,
  "messages": [
    {
      "message_id": 93410001,
      "from": "customer",
      "author": "Lena Vos",
      "body": "Hi, the invoice for order 4471 has the old VAT number on it. Can you send a corrected one?",
      "at": "2026-10-20T06:52:00Z"
    }
  ]
}

list_labels

The labels set up in your Trengo, with colour, channels and whether they are archived. Access: read. REST: GET /api/v1/trengo/labels. MCP: trengo_read → list_labels.

No parameters.

Returns the labels from Settings > Settings > Labels. Use the name in add_label, remove_label and the label filter. A label belongs to the channels chosen when it was created, and archived labels are marked so the agent does not add them.

Example response:

{
  "labels": [
    {
      "name": "Billing",
      "color": "#E5484D",
      "channels": [
        "Support email"
      ],
      "archived": false
    },
    {
      "name": "Delivery",
      "color": "#3E63DD",
      "channels": [
        "Support email",
        "WhatsApp"
      ],
      "archived": false
    }
  ]
}

list_assignees

The users and teams a conversation can be assigned to. Access: read. REST: GET /api/v1/trengo/assignees. MCP: trengo_read → list_assignees.

No parameters.

Returns the users and the teams of your Trengo with their IDs. Use user_id or team_id in assign_conversation. What your own user can see in the Assign menu is what comes back.

Example response:

{
  "users": [
    {
      "user_id": 4012,
      "name": "Sam de Boer"
    },
    {
      "user_id": 4015,
      "name": "Maya Okafor"
    }
  ],
  "teams": [
    {
      "team_id": 88,
      "name": "Billing team"
    },
    {
      "team_id": 91,
      "name": "Tech team"
    }
  ]
}

list_quick_replies

The quick replies of your Trengo with their type and text. Access: read. REST: GET /api/v1/trengo/quick-replies. MCP: trengo_read → list_quick_replies.

ParameterTypeRequiredDescription
typeenumnomessaging or email. Default: both.

Returns the quick replies from Settings > Settings > Quick replies. Type is messaging for channels such as Facebook, WhatsApp and Website chat, and email for email channels. The text comes back as written, tags included, and the agent fills in the details itself before reply_to_conversation sends.

Example response:

{
  "quick_replies": [
    {
      "name": "Refund timeline",
      "type": "email",
      "message": "Hi, your refund has been issued and shows on your statement within a few days."
    },
    {
      "name": "Parcel on its way",
      "type": "messaging",
      "message": "Your parcel is on its way and should arrive tomorrow."
    }
  ]
}

add_label

Adds a label to a conversation. Access: write. REST: POST /api/v1/trengo/conversations/{conversation_id}/labels. MCP: trengo_write → add_label.

ParameterTypeRequiredDescription
conversation_idintegeryesConversation ID from list_conversations or search_conversations.
labelstringyesLabel name from list_labels.

Uses the label icon of the conversation. A name that does not exist, is archived or is not set up for the conversation's channel fails at once, and the error lists the labels you can use. It reaches nobody and is undone with remove_label, so it runs without confirmation. An automation of yours that listens for a new label, such as a Zap on Ticket label added, still runs.

Example response:

{
  "conversation_id": 5120344,
  "labels": [
    "Billing"
  ]
}

remove_label

Removes a label from a conversation. Access: write. REST: DELETE /api/v1/trengo/conversations/{conversation_id}/labels. MCP: trengo_write → remove_label.

ParameterTypeRequiredDescription
conversation_idintegeryesConversation ID from list_conversations or search_conversations.
labelstringyesLabel name currently on the conversation.

Uses the cross icon on the label. Returns the labels that remain. It reaches nobody and add_label puts the label back, so it runs without confirmation.

Example response:

{
  "conversation_id": 5120344,
  "labels": []
}

set_reminder

Sets or clears the reminder that reopens a conversation in your inbox. Access: write. REST: PUT /api/v1/trengo/conversations/{conversation_id}/reminder. MCP: trengo_write → set_reminder.

ParameterTypeRequiredDescription
conversation_idintegeryesConversation ID from list_conversations or search_conversations.
remind_atstringnoDate and time to reopen the conversation, ISO 8601 with offset. Required unless clear is true.
clearbooleannoRemove the reminder. Default: false.

Uses the Bell icon. The conversation moves to your Reminders folder and returns to the inbox at the date and time you give. Pass clear to remove an existing reminder. It reaches nobody and one more call undoes it, so it runs without confirmation.

Example response:

{
  "conversation_id": 5120367,
  "reminder_at": "2026-10-26T09:00:00+01:00"
}

add_internal_note

Writes an internal note on a conversation, visible to your team and not to the customer. Access: write, asks the user first. REST: POST /api/v1/trengo/conversations/{conversation_id}/internal-notes. MCP: trengo_write → add_internal_note.

ParameterTypeRequiredDescription
conversation_idintegeryesConversation ID from list_conversations or search_conversations.
notestringyesPlain text of the note.

Adds a note to the thread, shown to your team only. A note can mention a colleague, so it can reach people. It cannot be edited or deleted through Cotlet. Returns the note ID and the time. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "conversation_id": 5120344,
  "message_id": 93410017,
  "created_at": "2026-10-20T07:05:00Z"
}

assign_conversation

Assigns a conversation to a user or to a team. Access: write, asks the user first. REST: POST /api/v1/trengo/conversations/{conversation_id}/assign. MCP: trengo_write → assign_conversation.

ParameterTypeRequiredDescription
conversation_idintegeryesConversation ID from list_conversations or search_conversations.
user_idintegernoUser ID from list_assignees. Use this or team_id.
team_idintegernoTeam ID from list_assignees. Use this or user_id.

Uses the Assign button of the conversation. Pass exactly one of user_id or team_id, both from list_assignees. The assignee sees the conversation in their inbox. A conversation that another person already took is returned with its current assignee and not changed. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "conversation_id": 5120344,
  "assigned_to": {
    "type": "user",
    "id": 4012,
    "name": "Sam de Boer"
  },
  "assigned_at": "2026-10-20T07:06:00Z"
}

reply_to_conversation

Sends a reply to the customer in the conversation's own channel. Access: write, asks the user first. REST: POST /api/v1/trengo/conversations/{conversation_id}/replies. MCP: trengo_write → reply_to_conversation.

ParameterTypeRequiredDescription
conversation_idintegeryesConversation ID from list_conversations or search_conversations.
messagestringyesText to send.
close_after_sendbooleannoSend and close in one step. Default: false.

Sends the message as you, by email, WhatsApp or whichever channel the conversation is on. A reply sent cannot be recalled through Cotlet. On WhatsApp, Trengo asks you to keep to WhatsApp's 24-hour limitation, and a template is the only way to start a conversation; this tool answers existing conversations only. Set close_after_send for Send and close. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "conversation_id": 5120391,
  "message_id": 93410022,
  "channel": "Email",
  "sent_at": "2026-10-20T08:14:00Z",
  "closed": false
}

close_conversation

Closes a conversation without sending a message. Access: write, asks the user first. REST: POST /api/v1/trengo/conversations/{conversation_id}/close. MCP: trengo_write → close_conversation.

ParameterTypeRequiredDescription
conversation_idintegeryesConversation ID from list_conversations or search_conversations.

Uses the checkmark above the ticket. It sends nothing to the customer itself, but Journeys, rules or a CSAT survey you set up may react to a closed conversation. To send a last message and close, use reply_to_conversation with close_after_send. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "conversation_id": 5120302,
  "status": "closed",
  "closed_at": "2026-10-20T09:10:00Z"
}

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

Connecting Trengo takes three steps: sign up, sign in to Trengo 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 Trengo to your agent.

  1. Create an account Sign up and add Trengo 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 Trengo in your Cloud Browser Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Trengo 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 Trengo 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.
Go through the new Trengo conversations. Label each one by topic (Billing, Delivery or Bug), assign Billing to the Billing team, Delivery to Sam and Bug to the Tech team, and leave an internal note with the reason. Leave unclear ones for me.

Call Trengo 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/trengo 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/trengo/conversations/5120344/assign \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"user_id":4012}'
  1. Read the result You get plain JSON back, ready for your script. A failed call costs nothing.
{
  "conversation_id": 5120344,
  "assigned_to": {
    "type": "user",
    "id": 4012,
    "name": "Sam de Boer"
  },
  "assigned_at": "2026-10-20T07:06:00Z"
}

How to use the Trengo REST API

Create your Cotlet API key

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

Connect Trengo in Cotlet and enable it for agents. Account access: Your own Trengo login at app.trengo.com. What your agent can do follows your user's permissions. You enter your 2-step verification yourself, in your own Cloud Browser.

Make your first Trengo API request

REST:

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

Read conversations 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": "trengo",
  "tool": "list_conversations",
  "result": {
    "conversations": [
      {
        "conversation_id": 5120344,
        "subject": "Invoice shows the wrong VAT number",
        "contact": "Lena Vos",
        "channel": "Email",
        "labels": [],
        "assigned_to": null,
        "last_message": {
          "from": "customer",
          "preview": "Hi, the invoice for order 4471 has the old VAT number on it. Can you send a corrected one?",
          "at": "2026-10-20T06:52:00Z"
        }
      }
    ],
    "next_cursor": null
  }
}

Returns the conversations of one folder of the inbox, newest first. Each row has the subject, the contact, the channel, the labels, the assignee and a preview of the last message with who wrote it and when. last_message_from filters each page you read; pass next_cursor back as cursor until it is null.

Use get_conversation for the full thread.

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.

Trengo workflows for agents and automations

ToolConnect throughExample workflow
n8nHTTP RequestOne conversation with its contact, labels, assignee and every message, internal notes included. Use get_conversation in your configured support report.
MakeHTTP > Make a requestThe labels set up in your Trengo, with colour, channels and whether they are archived. Use list_labels in your configured support report.
Python or Node.jsREST APIThe quick replies of your Trengo with their type and text. Use list_quick_replies in your configured support report.

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

Cotlet reads Trengo; 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 Trengo?

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 Trengo 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 Trengo changes, the tool pauses until we fix it.
  • Failed calls cost nothing.

Is it safe to connect Trengo to Cotlet?

Yes. You sign in to Trengo yourself, in your own Cloud Browser, and we never save your password. Your agents only get Trengo 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 Trengo integration?

No, Cotlet is independent of Trengo. Trengo's own API is too limited for this work. Cotlet works through your own Trengo account, the way you use Trengo in the browser.

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 Trengo in your console: your agents lose access at once and you stay signed in. Signing out of Trengo in the browser works too, and Reset browser deletes the whole profile.

Is there a Trengo MCP server on GitHub?

Zapier has a Trengo app. It starts a Zap when a message arrives, a label is added, an internal note is written or a call happens, and it can send a message or a WhatsApp template and find or create contacts. It does not list, label, assign or close conversations. Cotlet hosts those tools for your agent, signs in as you, and our team keeps them working.

ZapierCotlet
SetupConnect Zapier under Settings > Apps & Integrations in Trengo, then build one Zap per jobSign up, sign in to Trengo once, add one MCP server or API key
What it coversTriggers on new messages, label added, internal notes and calls; actions to send a message or template and manage contactsLists, searches and reads conversations, labels, assigns, adds notes and reminders, replies and closes
When it runsInstantly, the moment the event happens in TrengoOn a schedule, or when you or your agent start it; no event triggers
When Trengo changesZapier maintains its Trengo appOur team tests it daily and fixes it for you; failed calls are free
Your Trengo accessA connection you authorise in ZapierSigned in inside your own Cloud Browser in the EU, profile encrypted, only for the apps you enable, disabled for agents in one click
When access expiresYou reconnect the account in ZapierYour Cloud Browser keeps you signed in; if Trengo logs you out, your agent gets a link to sign in again
PriceA Zapier plan, on top of your Trengo planFree 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 Trengo 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 Trengo API cost?

Free 7-day trial with 2,000 credits, no card needed. After that, the Trengo 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 Trengo 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 Trengo 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 Trengo only after you enable it. When Trengo signs you out, your agent gives you a link to sign in again. Security
  • Revoking access: Press Disable for agents next to Trengo, sign out of Trengo 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.
  • Trengo's terms: You use your own Trengo account and stay responsible for following Trengo's terms. Cotlet is independent and not affiliated with Trengo. Terms
  • Contact: Questions about the company, security or an app: contact@cotlet.dev

Also listed on: Odel, mcpbeat

Trengo API and MCP: questions

How do I get access?

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

Do I need to be technical?

No. You sign in to Trengo 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 Trengo to Cotlet?

Yes. You sign in to Trengo yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Trengo 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 Trengo 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 Trengo 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 Trengo's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Trengo 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 Trengo 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?

Trengo 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 Trengo to ChatGPT or Claude?

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

What can ChatGPT do in Trengo?

With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Trengo: triage new conversations; reply to waiting customers; close resolved conversations. You ask in plain words, and anything that reaches other people waits for your OK first.

Does Cotlet use my Trengo API token?

No. Cotlet works in your own signed-in Trengo, so it needs no personal access token. The REST API, which Trengo limits to 120 requests per minute, is a separate way in.

Will Trengo ship its own MCP server?

Trengo's feature board lists "MCP server integration for AI" with the status Building and no date (read 20 Oct 2026). Votes there do not guarantee development, says Trengo. Cotlet covers the inbox jobs today.

Can my agent start a WhatsApp conversation?

No. Trengo starts a WhatsApp conversation only with an approved template from Inbox > Start a conversation, and the customer must have opted in. The tools here answer conversations that already exist, within WhatsApp's 24-hour limitation.

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

No. Every call to add_internal_note, assign_conversation, reply_to_conversation or close_conversation 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_label, remove_label and set_reminder run without asking, because they send nothing to anyone and one call undoes it.

Can I use the Trengo 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/trengo from the HTTP Request node.

Can I use the Trengo 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.