How to Use the Wati MCP in Pydantic AI

Q: What tools does Pydantic AI expose for Wati?

It exposes all seven tools, including sendsessionmessage and listwhatsappcontacts. The agent just calls the tool, and Pydantic ensures the return type is clean.

Q: Can I list available templates using Wati and Pydantic AI?

Yep. You can call listwhatsapptemplates to get a validated list of all your message templates, making sure your agent only attempts to send existing ones.

Q: What if I need conversation history with Wati and Pydantic AI?

Run the getwhatsappchathistory tool. You get the recent messages back, and Pydantic makes sure that message list structure is exactly what you expect it to be.

Guarantee Wati data structure integrity using Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Wati to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Handle contact records safely

The `get_whatsapp_contact_details` tool lets your agent fetch a user's profile. Because it uses Pydantic, if the API returns unexpected fields, your system fails loud with a validation error. No silent corruption—you know right away when the data structure is wrong.

Track and manage campaigns

You can use `list_broadcast_campaigns` to view all campaign status. The Pydantic validation guarantees that the list of campaigns you receive has predictable, structured fields. This level of type safety means your agent's business logic won't break just because Wati changed an internal field name.

Send messages with guaranteed payload

When sending a message using `send_template_message`, the tool ensures that the required template name and phone number are present. If the API response data is messy, Pydantic catches it. Correctness over speed. That's why you use this MCP Server.

Setup guide

Set up Wati MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "wati-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Wati tools.",
)

result = await agent.run("List recent Wati transactions")
print(result.output)

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 Pydantic AI

Pydantic validates every piece of data coming back from the Wati MCP Server. It forces the results—whether it's a message list or contact details—into Python objects you can trust.

It exposes all seven tools, including `send_session_message` and `list_whatsapp_contacts`. The agent just calls the tool, and Pydantic ensures the return type is clean.

Yep. You can call `list_whatsapp_templates` to get a validated list of all your message templates, making sure your agent only attempts to send existing ones.

Run the `get_whatsapp_chat_history` tool. You get the recent messages back, and Pydantic makes sure that message list structure is exactly what you expect it to be.

This server touches contact details and phone numbers. Because of the validation layer, you'll get reliable structures when dealing with sensitive user information like that.

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