How to Use the AT&T Messaging MCP in LangChain

Q: How do I handle AT&T Messaging SMS delivery tracking inside a LangChain agent?

You pass the getmessagestatus tool to your LangChain agent within a ReAct loop. The agent calls this tool using the message ID returned from a previous send step, monitoring the status until it confirms delivery.

Q: Can a LangChain chain automatically retire shortcodes using AT&T Messaging?

Yes, your LangChain chain uses the deleteshortcode tool when a campaign ends. The agent evaluates campaign performance metrics and triggers this tool to decommission the shortcode without manual intervention.

Q: How does LangChain handle bulk messaging errors with AT&T Messaging?

When sendbulksms returns the status array, LangChain parses the failed recipients. The agent then routes those specific numbers to a retry chain or logs them in LangSmith for debugging.

Q: How do I configure this MCP Server in my LangChain setup?

Install langchain-mcp-adapters and initialize the MultiServerMCPClient with the Vinkius endpoint. Then, call gettools() to connect your agent to the MCP connection so it can access the messaging functions.

Run multi-step communication chains with LangChain and direct AT&T Messaging control.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AT&T Messaging MCP to LangChain

Create your Vinkius account to connect AT&T Messaging 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 AT&T Messaging with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain automated campaign rollouts with LangChain

The `create_shortcode` tool provisions a new marketing campaign shortcode and returns its activation timeline directly to your LangChain agent. Your agent uses this timeline to schedule follow-up steps, feeding the newly generated shortcode straight into downstream prompt templates. By chaining this setup with your database, the agent reads your customer segments and builds the campaign parameters. You watch this entire sequence execute in LangSmith, checking exactly how the shortcode payload transitions from raw API output to active campaign assets.

Multi-step SMS validation in LangChain chains

Calling the `send_sms` tool sends transactional messages to E.164 phone numbers and returns a unique message ID. Within a LangChain ReAct loop using this MCP Server, the agent takes this message ID and feeds it directly into a monitoring loop to verify delivery. Instead of manual polling, the agent handles the logic, checking the status before triggering the next API call in your sequence. Your team gets a clear execution log of every SMS sent, complete with token usage and latency metrics for each step.

Run bulk SMS broadcasts with an MCP Server agent

Using the `send_bulk_sms` tool transmits texts to up to 164 phone numbers simultaneously, returning a job ID and individual delivery statuses. Your LangChain agent processes this array of statuses to identify failed numbers and automatically schedules retries. This MCP Server integration allows your agent to coordinate complex notification flows without hardcoded scripts. It reads the recipient list, triggers the bulk job, and routes the API response directly to your logging chain.

Setup guide

Set up AT&T Messaging 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 AT&T Messaging 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({
    "att-messaging-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 AT&T Messaging 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 AT&T Messaging. 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 AT&T Messaging 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 AT&T Messaging MCP in LangChain

You pass the `get_message_status` tool to your LangChain agent within a ReAct loop. The agent calls this tool using the message ID returned from a previous send step, monitoring the status until it confirms delivery.

Yes, your LangChain chain uses the `delete_shortcode` tool when a campaign ends. The agent evaluates campaign performance metrics and triggers this tool to decommission the shortcode without manual intervention.

When `send_bulk_sms` returns the status array, LangChain parses the failed recipients. The agent then routes those specific numbers to a retry chain or logs them in LangSmith for debugging.

Install `langchain-mcp-adapters` and initialize the `MultiServerMCPClient` with the Vinkius endpoint. Then, call `get_tools()` to connect your agent to the MCP connection so it can access the messaging functions.

The Vinkius sandbox isolates all execution, meaning your recipient phone numbers and message payloads never persist on the host. Every message transmission goes directly to the carrier network over encrypted channels.

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