Connector guide6-minute read10 MCP tools7 languages

How to Connect WATI to ChatGPT via MCP

Run your WATI WhatsApp Business inbox from your AI: list approved templates, find, add and update contacts, read a contact's chat history, assign conversations to team members, and send a template message. Session, interactive and bulk sends are installed switched off.

HCBy HelpCode teamUpdated 6 min read Open-source on GitHub

No credit card · 7-day trial · Self-host alternative available

WATI

WATI

Run your WATI WhatsApp Business inbox from your AI: list approved templates, find, add and update contacts, read a contact's chat history, assign conversations to team members, and send a template message. Session, interactive and bulk sends are installed switched off.

tools

10

Region

INTL

Category

Messaging

Authentication

Bearer Token

Required env vars

WATI_API_ENDPOINTWATI_ACCESS_TOKEN
Install in one click on Cloud

7-day free trial · No credit card

  • 7-day free trial
    No credit card required
  • GDPR & SOC 2 ready
    EU data residency, audit logs
  • Open-source on GitHub
    Open source · AGPL-3.0
  • Works with ChatGPT, Claude, Gemini
    Any MCP-compatible client

Skip the install. Get this working in under 2 minutes.

Start a free trial on cloud.anythingmcp.com, add the WATI in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.

Start free trial

Summary

Run your WATI WhatsApp Business inbox from your AI: list approved templates, find, add and update contacts, read a contact's chat history, assign conversations to team members, and send a template message. Session, interactive and bulk sends are installed switched off.

Try asking

Example prompts for WATI

Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.

WATI · live via MCP
Share
Opus 4.7

Claude is AI and can make mistakes. Please double-check responses.

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → WATI, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

WATI + ChatGPT

Run your WATI WhatsApp Business inbox from your AI: list approved templates, find, add and update contacts, read a contact's chat history, assign conversations to team members, and send a template message. Session, interactive and bulk sends are installed switched off.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

WATI_API_ENDPOINT, WATI_ACCESS_TOKEN

Step 1 — Get credentials

Setting up takes about 2 minutes. You need a WATI workspace on the Growth plan or higher, and its API Endpoint and Access Token.

  1. Sign in to WATI and open API Docs in the menu (in newer workspaces Connector → API).
  2. Copy the API Endpoint into WATI_API_ENDPOINT as WATI shows it, e.g. https://live-mt-server.wati.io/123456, without /api/v1 at the end. The number at the end is your workspace (tenant) id.
  3. Copy the Access Token into WATI_ACCESS_TOKEN without the word Bearer: WATI shows it as Bearer eyJ..., so paste only the part from eyJ on.
  4. Install the connector and run wati_list_message_templates: it lists your WhatsApp templates and shows that endpoint and token belong together.

API v1 only: the connector works with WATI's API v1. WATI's newer API v3 does not accept the token from the API Docs screen, so its extra features (conversation tags and status, channels, campaigns, credits) are not part of this connector. The token is sent only to your API Endpoint, and it stops working when the account password changes.

What it reads: your message templates with category, status (APPROVED, PENDING, REJECTED), language, header, body with its placeholders, footer and buttons; your contacts with WhatsApp number, name, opt-in, broadcast permission, custom attributes and teams, filtered by name, by an attribute or by creation date; and the chat history with one contact, newest first, with delivery status, operator and ticket events.

Numbers: WhatsApp numbers go in international format with the country code and without + or spaces, e.g. 919876543210. Where a tool asks for a contact you can also pass a WATI contact id. If your workspace has several WhatsApp numbers, the AI can choose which business number to use.

Templates and the 24-hour window: outside the 24 hours after the customer's last message, WhatsApp only allows approved templates, and only templates with status APPROVED can be sent. Inside the window, free text and reply buttons are allowed. Meta charges template messages per conversation.

Asks before every change: wati_send_template_message sends one template to one number and the customer receives it at once; wati_add_contact adds a contact with a name and custom attributes; wati_update_contact_attributes sets attributes such as order status or lead stage and leaves the others as they are. Before each of them the AI shows you the number, the template and values or the change, and waits for your yes. wati_assign_operator hands a chat to a team member by email, or back to the bot, and only changes the shared inbox.

Switched off at install: wati_send_session_message (free text in an open 24-hour session), wati_send_interactive_buttons (a message with up to three reply buttons) and wati_send_template_broadcast (one template to up to 1,000 numbers per call, and every recipient is messaged and charged). They reach customers directly, so an administrator turns them on deliberately, and even then the AI confirms every send with you.

Limits: about 10 requests per 10 seconds for contacts and messages, and 30 to 100 template sends per 10 seconds depending on your plan. A 429 means wait a few seconds and try again.

Common errors: 401 means the token is wrong, expired or still starts with Bearer. 403 means the token or your plan does not allow the call. 404 usually means a wrong API Endpoint. WATI also answers some failures with HTTP 200 and result false, for example an invalid number or a template that is not approved: the connector turns these into errors with WATI's text. A contact who never chatted with you has no chat history (Can't find Conversation). A successful send means WATI accepted the message, not that it was delivered.

The connector does not use API v3, create or delete templates, schedule campaigns or CSV sends, send media, files, list or CTA messages, build chatbots or segments, set up webhooks, handle WhatsApp Pay, or rotate the token.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in ChatGPT

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

ChatGPT adds MCP servers as plugins on its Plugins page, on the web and on paid plans. Developer mode is no longer needed. In a Business workspace only admins and owners can add one; in Enterprise and Edu an admin can grant the Create plugins with MCPs permission.

  1. Go to chatgpt.com/plugins, click +, then Add custom MCP server.
  2. Enter a name, e.g. Name: WATI.
  3. Under Connection, enter the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID and keep Authentication on OAuth.
  4. Select I understand and want to continue, then Create as a plugin. When ChatGPT asks, sign in to AnythingMCP and allow access.
  5. Install the new plugin from your personal plugins, then type @ in a chat and pick it.

Available tools

ToolWhat it does
wati_list_message_templatesList the workspace's WhatsApp message templates: id, name, category, status (APPROVED, PENDING, REJECTED), language, header, body with its…
wati_list_contactsList or search the workspace's contacts, page by page: id, WhatsApp number, name, phone, status, opt-in, broadcast permission, custom…
wati_get_messagesRead the chat history with one contact, newest first, page by page: message id, time, type, text, whether we sent it (owner), delivery…
wati_add_contactAdd a contact to WATI with a name and optional custom attributes
wati_update_contact_attributesSet custom attributes on a contact, e.g. order status, city or lead stage; attributes you do not pass stay as they are
wati_assign_operatorAssign a contact's conversation to a WATI team member by their email, or hand it back to the bot by leaving the email out
wati_send_template_messageSend one approved WhatsApp template to one number, the only way to write first or after the 24-hour window
wati_send_template_broadcastSend one approved template to many numbers at once (up to 1,000 per call) with values per recipient, as a WATI broadcast
wati_send_session_messageSend a free-text WhatsApp message to a contact who wrote to you in the last 24 hours (open session)
wati_send_interactive_buttonsSend a message with up to three reply buttons to a contact in an open 24-hour session, e.g. 'Track order' or 'Talk to us'

Example prompts

  • "Find the contact Priya Sharma and show me her last WhatsApp messages with us."
  • "Which of our approved templates fit an order shipped update, and which values do they need?"
  • "Send the order_shipped template to 919876543210 with name Rahul and order number 4512. Show me everything before it goes out."
  • "Set lead_stage to qualified for 919812345678 and assign the chat to [email protected]."
  • "List the contacts created today whose city is Pune."

FAQ

Does the free ChatGPT plan work with custom MCP servers? OpenAI documents custom MCP servers for paid plans only; the Free plan is not on its list.

Next steps

Was this guide helpful?

Your WATI agent is one click away.

Install the connector, paste the key, prompt ChatGPT. Free for 7 days, no credit card.

Related guides

Connectors

How to Connect WATI to Claude via MCP

Run your WATI WhatsApp Business inbox from your AI: list approved templates, find, add and update contacts, read a contact's chat history, assign conversations to team members, and send a template message. Session, interactive and bulk sends are installed switched off.

Connectors

How to Connect WATI to Cursor via MCP

Run your WATI WhatsApp Business inbox from your AI: list approved templates, find, add and update contacts, read a contact's chat history, assign conversations to team members, and send a template message. Session, interactive and bulk sends are installed switched off.

Connectors

How to Connect WATI to Gemini via MCP

Run your WATI WhatsApp Business inbox from your AI: list approved templates, find, add and update contacts, read a contact's chat history, assign conversations to team members, and send a template message. Session, interactive and bulk sends are installed switched off.

Connectors

How to Connect WATI to Meta Muse via MCP

Run your WATI WhatsApp Business inbox from your AI: list approved templates, find, add and update contacts, read a contact's chat history, assign conversations to team members, and send a template message. Session, interactive and bulk sends are installed switched off.

Connectors

WATI to MCP: Run Your WhatsApp Business Inbox from any AI Agent

Run your WATI WhatsApp Business inbox from your AI: list approved templates, find, add and update contacts, read a contact's chat history, assign conversations to team members, and send a template message. Session, interactive and bulk sends are installed switched off.

Connectors

How to Connect Avito to ChatGPT via MCP

Let your AI work with your Avito business account: list your ads and change their prices, read views, contacts and calls statistics, check autoload uploads and their errors, the feed format and your wallet, and read Avito Messenger chats. Sending messages and changing autoload settings are optional and off by default.