How to Use the Termii MCP in LangChain

Q: How does Termii help with messaging in LangChain?

The termii-mcp server exposes multiple tools—like sendsms and sendwhatsapp—that your agent can call sequentially. This lets you build a complete user journey, from initial contact to final message delivery.

Q: What data does Termii touch when used with LangChain?

The server handles account balance data (checkbalance), user authentication data (OTP codes), and various sender identifiers. All of this is managed through the MCP Server's defined tools.

Building complex communication agents 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 Termii MCP to LangChain

Create your Vinkius account to connect Termii 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 Termii with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step Messaging Flows

Use the `send_sms` tool to initiate a basic text message sequence. Your agent can then call `verify_otp` using the incoming code, making the entire process one chained action. This setup allows you to build complex communication logic where one step—like checking an account balance via `check_balance`—determines which subsequent messaging tool needs to run.

Rich Media and Authentication

Need more than just text? The `send_whatsapp` tool handles rich messages, while the `send_otp` function manages initial secure contact. Your agent can check if a user is registered by calling `list_sender_ids`, ensuring you only use valid sender IDs before sending anything. This combination lets your ReAct agent manage both setup and delivery: first checking credentials, then deciding whether to send an SMS or a WhatsApp update.

Stateful Agent Context

When running multi-server pipelines, the MCP Server tracks context. If one message fails, you can have your agent immediately retry by calling `send_sms` again, passing the last known user ID and error type. This means your LangChain agent doesn't forget what happened on step three; it just picks up exactly where it left off, making multi-channel communication reliable.

Setup guide

Set up Termii 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 Termii 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({
    "termii-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 Termii 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 Termii. 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 Termii 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 Termii MCP in LangChain

The `termii-mcp` server exposes multiple tools—like `send_sms` and `send_whatsapp`—that your agent can call sequentially. This lets you build a complete user journey, from initial contact to final message delivery.

Yes. The MCP Server supports SMS, WhatsApp, and OTP verification through distinct tools (`send_sms`, `send_whatsapp`, `send_otp`). Your agent determines which channel is best for the message based on internal logic.

The server handles account balance data (`check_balance`), user authentication data (OTP codes), and various sender identifiers. All of this is managed through the MCP Server's defined tools.

The server manages communication endpoints, allowing you to structure your chain calls to respect local carrier limits. You can check the balance via `check_balance` before initiating high-volume sending.

Absolutely. The combination of tools means you don't just send a message; you build a verifiable flow. Your agent can check the balance, list sender IDs, and then execute the final communication step.

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