Bring Whatsapp Api
to Pydantic AI
Learn how to connect Wati to Pydantic AI and start using 13 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Wati MCP Server?
Connect your Wati WhatsApp Business account to any AI agent and simplify how you engage with your customers through natural conversation and automated messaging workflows.
What you can do
- Direct Messaging — Send instant WhatsApp session messages to active contacts for real-time support and engagement.
- Template Automation — Send pre-approved WhatsApp templates to start conversations or send notifications with dynamic parameters.
- Contact Management — List and inspect your WhatsApp subscribers and contacts to keep your directory up-to-date.
- Chat History — Retrieve the complete message history for any specific contact to understand the conversation context.
- Template Catalog — List all available message templates to identify the best options for your communication strategy.
How it works
1. Subscribe to this server
2. Enter your Wati API Key and API Endpoint (found in your Wati API dashboard)
3. Start managing your WhatsApp communication from Claude, Cursor, or any MCP client
Who is this for?
- Customer Support Teams — quickly respond to inquiries and retrieve chat history via simple AI commands.
- Sales & Marketing — automate the sending of template-based notifications and manage lead contacts directly.
- Operations Managers — monitor communication flows and verify template availability without leaving the workspace.
Built-in capabilities (13)
Add a contact
Verify connectivity
Get contact details
Get template details
List broadcasts
List contacts
List messages
List tags
List message templates
Send media message
Send a session message
Send a template message
Update contact attributes
Why Pydantic AI?
Pydantic AI validates every Wati tool response against typed schemas, catching data inconsistencies at build time. Connect 13 tools through 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.
- —
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 in Pydantic AI
Wati and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Wati to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Wati in Pydantic AI
The Wati 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. All 13 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* 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
How Vinkius secures
Wati for Pydantic AI
Every tool call from Pydantic AI to the Wati MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
What is the difference between a session message and a template message?
Session messages can only be sent if the user has messaged you in the last 24 hours. Template messages are pre-approved by WhatsApp and can be used to initiate a conversation at any time.
How do I see the approved templates in my account?
Use the list_message_templates query. Your agent will retrieve the complete list of pre-approved WhatsApp templates available in your Wati dashboard.
Can I retrieve the last messages from a specific customer?
Yes! Use the list_chat_history tool and provide the customer's WhatsApp number. The agent will return the message history for that specific conversation.
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.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai