Can I send a WhatsApp message to a customer who hasn't messaged me first?

Yes, but you must use an approved template message. The `send_template_message` tool allows you to initiate communication using these templates. If the user has messaged you in the last 24 hours, you can use `send_session_message` for free-text replies.

How do I see what templates are available to send?

Use the `list_whatsapp_templates` tool. It will return all your approved and pending message templates, allowing you to choose the right one for your communication needs.

Can I check the delivery status of my broadcast campaigns via chat?

Yes. The `list_broadcast_campaigns` tool provides a list of your previous and active WhatsApp broadcasts, including their delivery statistics, so you can track performance directly from your agent.

Wati MCP Server for Pydantic AI 7 tools — connect in under 2 minutes

Name: Wati
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 7 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Wati through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Wati "
            "(7 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Wati?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Wati MCP Server

Connect your Wati account to any AI agent and power your customer communication on WhatsApp through natural conversation.

Pydantic AI validates every Wati tool response against typed schemas, catching data inconsistencies at build time. Connect 7 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Unified Messaging — Send approved WhatsApp template messages or free-text session replies to your customers
Contact Management — List all WhatsApp contacts in your Wati CRM and retrieve full profile details by phone number
Chat History — Retrieve the recent message history for any contact to provide personalized support or sales follow-ups
Template Discovery — List all approved and pending WhatsApp message templates available for outbound messaging
Broadcast Campaigns — Monitor previous and active WhatsApp broadcast campaigns and track their delivery status
Customer Roster — Quickly browse your customer list and their associated phone numbers directly from your agent

The Wati MCP Server exposes 7 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Wati to Pydantic AI via MCP

Follow these steps to integrate the Wati MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 7 tools from Wati with type-safe schemas

Why Use Pydantic AI with the Wati MCP Server

Pydantic AI provides unique advantages when paired with Wati through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Wati integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Wati connection logic from agent behavior for testable, maintainable code

Wati + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Wati MCP Server delivers measurable value.

Type-safe data pipelines: query Wati with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Wati tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Wati and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Wati responses and write comprehensive agent tests

Wati MCP Tools for Pydantic AI (7)

These 7 tools become available when you connect Wati to Pydantic AI via MCP:

get_whatsapp_chat_history

Provide the contact’s phone number. Retrieves the recent message history for a specific contact

get_whatsapp_contact_details

Retrieves profile details for a specific WhatsApp contact by phone number

list_broadcast_campaigns

Lists previous and active WhatsApp broadcast campaigns

list_whatsapp_contacts

Lists all WhatsApp contacts in the Wati CRM

list_whatsapp_templates

Lists all approved and pending WhatsApp message templates

send_session_message

Sends a free-text session message to a user

send_template_message

Requires the template name and target phone number. Sends an approved WhatsApp template message

Example Prompts for Wati in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Wati immediately.

"List all my WhatsApp contacts in Wati."

"Send the 'order_confirmation' template to +123456789."

"What was my last conversation with +123456789 about?"

Troubleshooting Wati MCP Server with Pydantic AI

Common issues when connecting Wati to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Wati + Pydantic AI FAQ

Common questions about integrating Wati MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Wati MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.