How to Use the NumVerify MCP in Pydantic AI

Q: How do I add NumVerify to a Pydantic AI agent?

Instantiate the MCPToolset with the server URL and pass it to your Agent's toolsets parameter. The agent automatically discovers tools like validatephone and enforces their schemas.

Q: Can I run this server locally during development?

Yes, but you must run the MCP Server externally. The MCPToolset class connects to the running instance over HTTP, allowing you to test your validation logic offline.

Guard your Pydantic AI pipelines against toxic phone inputs with strict NumVerify type-safe validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NumVerify MCP to Pydantic AI

Create your Vinkius account to connect NumVerify 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 NumVerify with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe carrier lookups in Pydantic AI

`get_phone_carrier` retrieves network provider details and validates the response against strict runtime types. Your Pydantic AI agent catches any unexpected payload structures before they pollute your application state. If the carrier database returns malformed JSON, the framework raises an explicit validation error. This guarantees that your downstream billing systems only receive clean, predictable data.

Enforce line type checks via this MCP Server

This MCP Server provides `get_phone_line_type` to distinguish mobile, landline, and virtual numbers. Your Pydantic AI agent maps these categories directly to your internal Python Enums. You eliminate silent failures caused by unexpected string values. The agent rejects invalid line types at runtime, ensuring your SMS notification systems never attempt to message a landline.

Validate and clean phone inputs instantly

`validate_phone` parses international dialing codes and formats the raw string input. Your Pydantic AI agent uses this tool to normalize user-submitted numbers into the standard E.164 format. This prevents database duplication and ensures consistent formatting across your entire system. The agent handles the parsing logic, leaving your core application clean and readable.

Setup guide

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

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

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

Instantiate the `MCPToolset` with the server URL and pass it to your Agent's `toolsets` parameter. The agent automatically discovers tools like `validate_phone` and enforces their schemas.

The framework fails loudly with a validation error. This prevents your agent from hallucinating properties or passing corrupted telecom metadata to your database.

Yes. You can connect your Pydantic AI agent to the MCP Server using either Streamable HTTP or Server-Sent Events (SSE) depending on your network setup.

Yes, but you must run the MCP Server externally. The `MCPToolset` class connects to the running instance over HTTP, allowing you to test your validation logic offline.

Your phone data stays private. All data transmission occurs over secure HTTPS connections directly to the isolated V8 sandbox. No phone numbers are written to disk or retained after the validation check completes.

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