How to Use the TeleSign MCP in LangChain

Q: How do I use TeleSign with LangChain for sign-up fraud prevention?

You construct a multi-step ReAct agent. The agent uses scorephone first, and based on the risk output, it decides whether to initiate an SMS or push verification flow.

Q: Can LangChain manage multiple authentication methods with TeleSign?

Absolutely. You can chain calls like this: first check getphonetype, then attempt sendpushverification. If that fails, the agent automatically tries sendsms next.

Q: Does LangChain support checking TeleSign account status?

Yes. You can use the checktelesignstatus tool in your chain to ensure the API connection is live before attempting any verification calls, preventing runtime errors.

Q: What data does TeleSign provide regarding phone identity for LangChain?

The server provides phone intelligence via getphoneid and a risk assessment through scorephone. This allows your agent to make decisions based on the number's perceived trustworthiness.

Q: Is TeleSign reliable for LangChain development?

The MCP Server provides status checks like checkdeactivation, so you always know if a number is active before attempting any verification, making your chains more reliable.

Build multi-step identity pipelines with LangChain.

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 LangChain

Create your Vinkius account to connect TeleSign to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dynamic Verification Chains for LangChain

The agent determines the necessary steps by chaining tools together. For instance, it first calls `score_phone` to evaluate risk. If the score is high, it immediately proceeds to verify connectivity using `check_telesign_status`. The output of one function becomes the input for the next tool call in your chain. This makes complex flows—like checking a number's status and then deciding between `send_sms` or `send_push_verification`—easy to implement.

Handling Phone Identity Lifecycle with MCP Server

You can model the entire phone lifecycle in your chain. Start by getting basic info using `get_phone_id`, then check the number's type via `get_phone_type`. This lets you build a robust pre-check step before committing to sending a code. You also manage the state of the account, checking for deactivation with `check_deactivation` and verifying if the user's current status is valid using `check_verification`.

Orchestrating Fraud Prevention Workflows

Design a full fraud prevention path that handles multiple verification methods. If an SMS fails, your agent can automatically fall back to a voice check using `send_voice_verification`. This sequence of calls ensures maximum coverage. The system allows you to send general codes via `send_verification` or specific messages through `send_sms`, letting the chain decide which method minimizes user friction while maximizing security.

Setup guide

Set up TeleSign MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes TeleSign tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "telesign-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent TeleSign transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You construct a multi-step ReAct agent. The agent uses `score_phone` first, and based on the risk output, it decides whether to initiate an SMS or push verification flow.

Absolutely. You can chain calls like this: first check `get_phone_type`, then attempt `send_push_verification`. If that fails, the agent automatically tries `send_sms` next.

Yes. You can use the `check_telesign_status` tool in your chain to ensure the API connection is live before attempting any verification calls, preventing runtime errors.

The server provides phone intelligence via `get_phone_id` and a risk assessment through `score_phone`. This allows your agent to make decisions based on the number's perceived trustworthiness.

The MCP Server provides status checks like `check_deactivation`, so you always know if a number is active before attempting any verification, making your chains more reliable.

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