How to Use the Wati MCP in Claude Code

Q: Can I audit templates using Claude Code?

Yes, simply run a command that executes listwhatsapptemplates. This outputs all approved and pending template names, which is critical before deployment.

Q: What kind of messages can be sent via the MCP Server in Claude Code?

You've got two options: structured outreach using sendtemplatemessage, or free-form conversation replies using sendsessionmessage. Both are reliable for headless execution.

Q: How do I check contacts using the MCP Server in Claude Code?

Run listwhatsappcontacts to get a full dump of all Wati contacts. The output is perfect for scripting because you can easily pipe that data into other commands, like filtering by status.

Run unattended WhatsApp tasks and manage contacts using Claude Code in CI/CD pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wati MCP to Claude Code

Create your Vinkius account to connect Wati to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Wati with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Message Deployment via Scripts

The `send_template_message` tool lets you script message deployment. If you're running a nightly cron job, this ensures every recipient gets the exact same, approved template without manual intervention. Similarly, piping output from `send_session_message` means your CI/CD pipeline can handle real-time conversation threads and respond accordingly.

Bulk Data Retrieval for Pipelines

Use the `list_whatsapp_contacts` tool to pull all Wati contacts into a variable that other scripts can read. You can then write subsequent steps that process this list, like updating metadata or sending unique notifications. To keep track of outreach efforts, piping the output of `list_broadcast_campaigns` lets you build reports on which campaigns are currently active.

Contextual Data Logging

If a script needs to analyze a conversation, use `get_whatsapp_chat_history`. Piping this output allows your pipeline to feed the raw message data into another tool for analysis or auditing. For quick lookups on user profiles, running `get_whatsapp_contact_details` lets you grab specific details about a phone number and log them immediately after a successful transaction.

Setup guide

Set up Wati MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see wati-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Wati transactions." It will automatically discover and invoke the available Wati tools.

Terminal

claude mcp add --transport http wati-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Wati MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "wati-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Wati. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Wati now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Wati MCP in Claude Code

You run the MCP Server as part of your shell script or container job. You call the functions—like `list_whatsapp_templates`—and pipe the JSON output directly to subsequent commands for processing.

Yes, simply run a command that executes `list_whatsapp_templates`. This outputs all approved and pending template names, which is critical before deployment.

You've got two options: structured outreach using `send_template_message`, or free-form conversation replies using `send_session_message`. Both are reliable for headless execution.

This server handles communication state, touching sensitive contact details, phone numbers, message history records, and template metadata.

Run `list_whatsapp_contacts` to get a full dump of all Wati contacts. The output is perfect for scripting because you can easily pipe that data into other commands, like filtering by status.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript