How to Use the TNZ Communications MCP in LangChain

Q: How do I connect the TNZ Communications MCP Server to my LangChain setup?

Install the langchain-mcp-adapters package and configure the MultiServerMCPClient with the Vinkius endpoint. This exposes the entire suite of TNZ tools directly to your LangChain agent.

Q: Can LangChain agents handle message templates with TNZ Communications?

Yes. Your LangChain agent can call listmessagetemplates to fetch pre-configured layouts. It then uses those templates to format outbound payloads before dispatching them.

Q: How does LangChain handle connection failures with the TNZ Communications MCP Server?

You can run checkapihealth within your LangChain initialization code. This checks the connection to the TNZ API before starting any long-running agent chains.

Q: Can my LangChain agent monitor the prepaid budget of TNZ Communications?

Yes. Your agent can call getaccountbalance to check remaining credits. This lets you pause automated messaging chains before they run out of funds.

Run multi-step communication chains in LangChain using direct SMS, TTS voice, and fax tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect TNZ Communications MCP to LangChain

Create your Vinkius account to connect TNZ Communications 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 TNZ Communications with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain messaging tools with LangChain agents

LangChain agents can coordinate multi-step workflows by executing `send_sms_message` and immediately checking outcomes. Instead of manual scripting, your agent evaluates real-time responses to decide whether to trigger a fallback channel or escalate the alert. This declarative chaining lets you feed the output of one step directly into the next. For instance, you can retrieve inbound text replies using `list_received_sms_replies` to branch your LangChain logic dynamically based on user feedback.

Automate voice alerts and manage costs

When critical events require immediate attention, your LangChain agent can run `send_tts_voice_call` to read alerts aloud to on-call engineers. This moves beyond passive notifications, turning your LLM chains into active responders that dial phone numbers when thresholds are breached. To keep operational costs under control, the agent can periodically invoke `get_messaging_usage_report` within the same chain. You can also trigger legacy workflows by using `send_digital_fax` to transmit PDF documents to traditional fax machines.

Manage contacts and verify delivery

Keep your recipient list updated by letting your LangChain run `create_tnz_contact` whenever new users sign up. The agent can also pull your existing phonebook using `list_tnz_contacts` to clean up old records on the fly. Once messages are out, the agent tracks their path using `get_message_delivery_status` to confirm receipt. You can also organize these recipients by querying `list_contact_groups` to target specific segments.

Setup guide

Set up TNZ Communications 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 TNZ Communications 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({
    "tnz-communications-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 TNZ Communications 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 TNZ Communications. 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 TNZ Communications 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 TNZ Communications MCP in LangChain

Install the `langchain-mcp-adapters` package and configure the `MultiServerMCPClient` with the Vinkius endpoint. This exposes the entire suite of TNZ tools directly to your LangChain agent.

Yes. Your LangChain agent can call `list_message_templates` to fetch pre-configured layouts. It then uses those templates to format outbound payloads before dispatching them.

You can run `check_api_health` within your LangChain initialization code. This checks the connection to the TNZ API before starting any long-running agent chains.

Yes. Your agent can call `get_account_balance` to check remaining credits. This lets you pause automated messaging chains before they run out of funds.

All phone numbers and message payloads sent via this MCP server are processed inside an isolated Vinkius container. We use ephemeral, zero-trust environments so that no communication logs or contact details are stored persistently on the hosting platform.

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