How to Use the TeleSign MCP in Pydantic AI

Q: What is the sequence for phone checks using TeleSign and Pydantic AI?

You should start by calling getphoneid, which provides the base data. You can then follow up with scorephone to get a risk metric, making your entire workflow predictable and reliable.

Q: Does TeleSign help with system health checks for Pydantic AI?

Yes. You can use checktelesignstatus to verify API connectivity before running any critical operation. This type-safe approach makes sure you know the service is ready before your agent tries to write data.

Type-safe identity validation 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 TeleSign MCP to Pydantic AI

Create your Vinkius account to connect TeleSign 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 TeleSign with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Phone Identity Structure

You can get raw phone data using `get_phone_id`, and then refine that output by calling `get_phone_type`. Because the response is Pydantic-validated, you know exactly what fields to expect back. This makes your agent's logic reliable. The structured output means you don't have to worry about silent data corruption from unexpected API field names.

Control Verification Flow with Type Safety

The system requires specific inputs for each check, like running `check_deactivation` before proceeding. This forces a predictable workflow and makes your agent's steps auditable. If you need to verify the status of an existing process, use `check_verification`. The Pydantic layer ensures the returned success or failure state is always correct.

Execute Code-Validated Authentication

Authentication steps are clearly defined. You can send a code using `send_verification` or push it out via `send_push_verification`. The type safety guarantees that the parameters (like the recipient number) are always in the right format. Even if you fall back to SMS (`send_sms`), the structured data contract means your agent handles the resulting confirmation status without guesswork.

Setup guide

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

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

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

Pydantic validates every MCP response against a defined schema at runtime. If the API returns unexpected data, your agent fails loudly with a validation error, meaning no hallucinated or corrupted fields slip through.

You should start by calling `get_phone_id`, which provides the base data. You can then follow up with `score_phone` to get a risk metric, making your entire workflow predictable and reliable.

Absolutely. Your agent can attempt several methods sequentially—like `send_push_verification`, followed by `send_sms`—and the structured output ensures you always know which method ultimately succeeded.

Yes. You can use `check_telesign_status` to verify API connectivity before running any critical operation. This type-safe approach makes sure you know the service is ready *before* your agent tries to write data.

The server touches phone identity data. The structured nature of the tools means that only specific, expected fields are returned upon execution, limiting exposure and ensuring the data is handled predictably by your agent.

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