How to Use the Vonage MCP in Pydantic AI

Q: How do I use Vonage and Pydantic AI for SMS communications?

You call sendsms, providing the sender name and E.164 number. Because of Pydantic, you'll receive a guaranteed structure confirming the message was sent successfully.

Q: How do I manage my virtual numbers with Vonage and Pydantic AI?

You use listrentednumbers to get the list. If you update a number's webhook, updatenumberwebhook returns structured data that your agent can immediately trust.

Q: Can I check account balances with Vonage and Pydantic AI?

Yes. You run getaccountbalance. The result is a validated, typed object representing the current credit amount in your Vonage account.

Build type-safe Vonage integrations with 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 Vonage MCP to Pydantic AI

Create your Vinkius account to connect Vonage 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 Vonage with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sending Structured Messages via MCP Server

When you send a message, you want to know exactly what happened. Use `send_sms` or the WhatsApp/Viber tools to dispatch messages, but more importantly, Pydantic validates that the response structure is correct. The agent doesn't proceed if the data format is wrong—it fails loudly. This prevents silent corruption when communicating via Vonage.

Validating Verification Flows with Pydantic AI

Identity verification requires precise handoffs. The `start_verification` tool initiates the flow, and the agent then uses `check_verification_code` to confirm the user's input. Since responses are typed, you get immediate validation on success or failure. This makes your entire 2FA process robust; if the API returns unexpected data, Pydantic catches it.

Managing Account Context with Vonage and Pydantic AI

Need to check available resources? Run `get_account_balance` to get a validated credit figure. You can also confirm pricing details using `get_country_pricing`. Everything comes back as a predictable, typed object. This level of data correctness is non-negotiable when building production systems with Pydantic AI.

Setup guide

Set up Vonage 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": {
        "vonage-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Vonage 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 Vonage. 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 Vonage 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 Vonage MCP in Pydantic AI

You call `send_sms`, providing the sender name and E.164 number. Because of Pydantic, you'll receive a guaranteed structure confirming the message was sent successfully.

The agent fails loudly with a validation error. It won't accept or process hallucinated fields or corrupted data, ensuring your application remains correct and safe.

You use `list_rented_numbers` to get the list. If you update a number's webhook, `update_number_webhook` returns structured data that your agent can immediately trust.

Yes. You run `get_account_balance`. The result is a validated, typed object representing the current credit amount in your Vonage account.

The server handles phone numbers (E.164), account balance integers, OTP codes, and country pricing strings, all validated against strict models.

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