Can I send WhatsApp messages using this server?

Yes. The `send_whatsapp_message` tool allows you to send outbound WhatsApp messages through the Vonage Messages API. You'll need a verified WhatsApp Business Number configured in your Vonage account as the sender.

How do I implement two-factor authentication (2FA)?

You can use the `start_verification` tool to send an OTP code to a user's phone. Once the user receives the code, use `check_verification_code` with the `request_id` to validate it. Your agent can handle the entire flow through a single conversation.

Can I check how much sending an SMS will cost me?

Absolutely. Use the `get_country_pricing` tool and provide the ISO country code (e.g., 'US' or 'GB'). Your agent will return the outbound SMS pricing for that region, helping you estimate costs before sending.

Vonage MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Vonage
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Vonage 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 Vonage "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Vonage?"
    )
    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 Vonage MCP Server

Connect your Vonage account to any AI agent and power your global communications through natural conversation.

Pydantic AI validates every Vonage tool response against typed schemas, catching data inconsistencies at build time. Connect 10 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

Multi-Channel Messaging — Send outbound messages via SMS, WhatsApp Business, and Viber with ease
2FA & Verification — Start and check identity verification requests (OTP) to secure your user accounts
Number Management — List all virtual phone numbers rented by your account and update their inbound webhooks
Account Insights — Check your real-time account credit balance and monitor spending directly from your agent
Global Pricing — Retrieve outbound SMS pricing for any country to estimate communication costs accurately
Virtual Numbers — View caller ID capabilities (SMS, Voice) for all your rented virtual numbers

The Vonage MCP Server exposes 10 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 Vonage to Pydantic AI via MCP

Follow these steps to integrate the Vonage 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 10 tools from Vonage with type-safe schemas

Why Use Pydantic AI with the Vonage MCP Server

Pydantic AI provides unique advantages when paired with Vonage 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 Vonage integration code

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

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

Vonage + Pydantic AI Use Cases

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

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

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

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

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

Vonage MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Vonage to Pydantic AI via MCP:

cancel_verification_request

Aborts an active verification request

check_verification_code

Checks the OTP code submitted by a user for an active verification request

get_account_balance

Retrieves the current Vonage account credit balance

get_country_pricing

Provide the ISO 3166-1 alpha-2 country code. Retrieves outbound SMS pricing for a specific country

list_rented_numbers

Lists all virtual phone numbers rented by the account

send_sms

Provide a sender name (alpha or number) and a target phone number in E.164 format. Sends an outbound SMS message via Vonage

send_viber_message

Provide your specific Viber Publisher ID. Sends a Viber service message via Vonage

send_whatsapp_message

Requires a verified WhatsApp Business Number as the sender. Sends a WhatsApp message via the Vonage Messages API

start_verification

Provide the target number and your brand name. Starts a 2FA identity verification by sending an OTP code

update_number_webhook

Requires the number in E.164 format. Updates the inbound SMS callback URL for a virtual number

Example Prompts for Vonage in Pydantic AI

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

"Send an SMS to +123456789 saying 'Your order is ready for pickup!'."

"Start a verification for number +123456789 with brand 'MyCoolApp'."

"What is my current account balance and the SMS price for the UK?"

Troubleshooting Vonage MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Vonage + Pydantic AI FAQ

Common questions about integrating Vonage 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 Vonage MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.