Trengo API and MCP server

Trengo's own API has no quick replies or ticket reminders, and nothing built for an AI agent to work your inbox. Sign in to Trengo once in your own Cloud Browser, and your AI agent does the work there for you. The same tools work over MCP for agents and as a REST API for scripts.

Not affiliated with Trengo.

Trengo has no API for this. So we run one for you.

Trengo's own API, a GitHub MCP server and Cotlet compared
What you need Trengo's APIGitHub MCP serverCotlet
Agent tools, quick replies, reminders No No Yes, 13 tools
Acts as you, signed in 24/7 No No Yes, Cloud Browser
Fixed for you when Trengo changes N/A No Yes, tested every 6h
Runs with your laptop off N/A No Yes, hosted

Checked Oct 20, 2026. 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

Your own Cloud Browser, on 24/7. Sign in once. We keep it connected.

  1. 01Sign in to Trengo in your own Cloud Browser

  2. 02Connect it for your agents

  3. 03Cotlet keeps it signed in and working

How do I connect Trengo to Claude, ChatGPT or my code?

AI agents connect over MCP, scripts call the REST API. Both reach the same 13 tools with one API key.

For AI agents: MCP

Add Cotlet to your agent once. Trengo and every other app you connect show up as its tools.

  • Claude
  • ChatGPT
  • OpenClaw
  • Hermes
  • GrokBot
  • Cursor
  • n8n
  • Any MCP client
  1. 1

    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.

For scripts: REST API

Every tool is an endpoint under /api/v1/trengo with its own method and path, such as POST /api/v1/trengo/conversations/{conversation_id}/assign, with the same API key. Our open-source repo has ready scripts to start from.

REST API docs

What can the Trengo API and MCP server do?

13 tools on your own Trengo account. Agents call them as operations of the MCP tools trengo_read and trengo_write; scripts call each one at its own REST endpoint, with the same inputs and answers.

Trengo tools in Cotlet's MCP server and REST API
Tool What it does Access
list_conversations Conversations in an inbox folder, with channel, labels, assignee and the last message. read
search_conversations Conversations that match a ticket number, name, phone number, email address or keywords. read
get_conversation One conversation with its contact, labels, assignee and every message, internal notes included. read
list_labels The labels set up in your Trengo, with colour, channels and whether they are archived. read
list_assignees The users and teams a conversation can be assigned to. read
list_quick_replies The quick replies of your Trengo with their type and text. read
add_label Adds a label to a conversation. write
remove_label Removes a label from a conversation. write
set_reminder Sets or clears the reminder that reopens a conversation in your inbox. write
add_internal_note Writes an internal note on a conversation, visible to your team and not to the customer. writeasks first
assign_conversation Assigns a conversation to a user or to a team. writeasks first
reply_to_conversation Sends a reply to the customer in the conversation's own channel. writeasks first
close_conversation Closes a conversation without sending a message. writeasks first

Scroll the table for all 13 tools.

Ask in plain words. Your agent does the rest.

Is it safe to connect Trengo?

You sign in yourself in your own Cloud Browser, we never save your password, and anything that reaches your readers waits for your OK. The browser profile is encrypted in the EU. Independent scanners grade cotlet.dev A+.

How much do the Trengo API and MCP server cost?

One price for both: a tool call costs the same over MCP or REST. Free 7-day trial with 2,000 credits, no card needed. Then one-time credit packs, no subscription, valid 12 months. Most calls use 25 credits, and your Cloud Browser uses 50 credits a day while Trengo is enabled for agents, so 20 calls a day come to 550 credits.

Cotlet credit packs: price, credits and calls at 25 credits each
Credits Price, one time Calls at 25 credits Per 1,000 credits
5,000 $29 200 $5.80
15,000 $79 600 $5.27
32,000 $149 1,280 $4.66
60,000 $249 2,400 $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.

Questions

Does Trengo have an 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.

How do I get access?

Sign up free, open Trengo under Integrations in the console and press Request access. Your free trial starts with your account, no card needed.

Is the MCP server different from the API?

No, only the way in. Cotlet builds each integration as a REST API and puts an MCP server on top, so both have the same 13 tools, the same inputs and answers, one API key and one price. AI agents such as Claude, ChatGPT or Cursor use MCP; scripts, cron jobs and HTTP steps in n8n, Make or Zapier use the REST API.

What is the Cloud Browser?

Your own Chrome that Cotlet runs for you in the EU, around the clock. You open it from the console, sign in to Trengo yourself and press Enable for agents. Your agent's calls go through it, from its IP with its cookies, so Trengo sees the browser you signed in with. Password saving is off and the profile is stored encrypted with AES-256-GCM.

Can my agent act without asking me?

Not on anything that reaches other people: add_internal_note, assign_conversation, reply_to_conversation, close_conversation wait for your OK by default. You can switch that off per tool for scheduled runs.

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.

Should I use a Trengo MCP server from GitHub instead?

Pick one if you want the code on your own computer and do not mind the upkeep: you install it, sign it in and fix it when Trengo changes. Pick Cotlet if you want it hosted and kept working for you.

Can I use it in n8n, Make or Zapier?

Yes. Add https://cotlet.dev/mcp/v1 in n8n's MCP Client node, or call the REST endpoints from an HTTP step in Make or Zapier.

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 Cotlet affiliated with Trengo?

No. Cotlet is independent and not affiliated with Trengo.

Give your agent access to Trengo.

Free 7-day trial with 2,000 credits, no card needed.