- CONTEXT
- DRAFTING
- SENDING
- HUMAN
Short answer
How can I use my AI to reply to Trengo messages?
Your agent pulls recent conversation history from Trengo and sends replies across your active channels. You get a direct way to handle customer chats without switching tabs. Here is how the process works.
The outcomes.
Where your replies land.
Depending on what you ask, your AI will do one of these four things.
CONTEXT
Read recent history
The AI looks at what customers said in Trengo. You get the full context of the conversation before you decide how to reply.
DRAFTING
Write reply drafts
The AI generates a response based on the message history. You can review the text before it ever reaches the customer.
SENDING
Deliver messages
Your AI sends the text directly to the customer on their original channel. This keeps the conversation moving without manual typing.
HUMAN
Flag for review
If a message is too complex, the AI stops. You stay in control of the high-stakes or sensitive conversations.
The workflow
What your AI does when a message arrives.
The AI follows a specific sequence to move from reading a thread to sending a response.
Fetch the thread
The AI looks up the most recent messages in your Trengo inbox to understand the current situation.
list_messagesAnalyze the intent
Your agent reads the history to figure out what the customer actually needs and what tone to use.
list_messagesCompose the reply
The AI writes a response that fits the context of the previous messages.
list_messagesPost the response
The AI pushes the final text back to the customer through the appropriate channel.
send_message
Try it
Copy these to start.
Use these prompts to trigger the Trengo Connector.
Starting points
These are just ways to kick things off. Swap out the specific channel or customer name for your actual data.
Trengo Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_A8u1cVikv6oTvCUnABKUk7KeTnNuAWPNBEmEQcMW/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Trengo capabilities are ready to use.
{
"mcpServers": {
"trengo-mcp": {
"url": "https://edge.vinkius.com/vk_preview_A8u1cVikv6oTvCUnABKUk7KeTnNuAWPNBEmEQcMW/mcp"
}
}
}List the most recent messages from the WhatsApp channel.
Read the last five messages from the support thread and draft a reply.
Send a message to the customer in the Instagram inbox saying their order is ready.
Check the recent messages in the email channel to see if anyone is asking about shipping.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Trengo once, then ask.
Just click the link to connect your account. Your credentials stay encrypted, and you can start using these tools in your AI client immediately.
Connect Trengo to your AIFAQ
How the Trengo Connector behaves
- 01
Can the AI delete messages in Trengo?
No. The AI can only list messages and send new ones.
- 02
Does the AI automatically reply to every customer?
No. The AI only responds when you specifically ask it to via your AI client.
- 03
Can I see what the AI is going to say before it sends?
Yes. You can ask the AI to draft a response first so you can review it before telling it to send.
- 04
Which channels can the AI use?
The AI can use any channel currently connected to your Trengo account, such as WhatsApp, Instagram, or Email.
- 05
Can the AI create new contact profiles?
No. The tools are limited to reading message history and sending messages.
More questions about Trengo? See everything the Trengo Connector can do
Connect Trengo to Claude, Cursor, ChatGPT & more
