How to Use the Telebroad MCP in LangChain

Q: What is the most efficient way to use Telebroad with LangChain?

Start by mapping out your ideal workflow steps. Use listphonedestinations early on, as this provides a foundational map of all available extensions for subsequent communication tasks.

Orchestrate Complex Actions with LangChain and MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Telebroad MCP to LangChain

Create your Vinkius account to connect Telebroad to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Telebroad with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Step Communication Routing

You can build agent chains that handle complex communication flows. For example, an agent first uses `list_phone_destinations` to find the correct extension, then calls `send_call(extension)` to initiate contact. This flow means your AI client doesn't just call a tool; it decides the whole sequence. It’s perfect for building multi-step reasoning pipelines that require multiple actions before reaching a goal.

Automated Message Handling via MCP Server

An agent can check communication history, decide what's needed, and act on it. A chain might first call `list_sms_conversations`, then use `get_sms_messages` to read the thread, and finally generate a response using an external API. This sequence allows you to automate workflows that depend on reading multiple data points before sending a final action via tools like `send_sms`.

Real-Time Call Management

You can create chains designed for live call management. An agent could monitor the status using `list_active_calls`, detect when it needs to terminate a connection, and then execute `hangup_call` automatically. This capability lets your AI client handle dynamic situations without human intervention, making sure resources like active calls are managed correctly by the MCP Server.

Setup guide

Set up Telebroad 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 Telebroad 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({
    "telebroad-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 Telebroad 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 Telebroad. 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 Telebroad 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 Telebroad MCP in LangChain

LangChain agents can interpret and act upon historical data. You simply instruct your agent to check past activity, and it calls `list_call_history` to get the logs needed for its next decision.

Yes. The core strength is chaining—the output of one tool (like a user profile from `get_profile`) becomes the input context for the next tool, allowing deep, multi-step logic.

LangChain can access and process structured communication logs, including details found in `list_call_history` and user profiles from `get_profile`. This is handled entirely by your agent's controlled tool execution.

Absolutely. By chaining tools, you move beyond simple API calls. You can build full decision trees: check status, read history, and then initiate a call—all within one agent pipeline.

Start by mapping out your ideal workflow steps. Use `list_phone_destinations` early on, as this provides a foundational map of all available extensions for subsequent communication tasks.

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