How to Use the AT&T 5G MCP in LangChain

Q: How do I use the AT&T 5G tools in a LangChain ReAct agent?

Just pass the tools from client.gettools() into your createagent function. The agent will automatically see the function definitions for tools like verifynumber and getdevicelocation and know when to call them based on your prompt.

Q: Can my LangChain agent combine AT&T 5G data with other APIs?

Yes, that's the whole point. A chain can call checksimswap from this MCP server, then use the result to query your own user database through a different integration, all in one sequence.

Q: What's the best way to manage network slices with AT&T 5G and LangChain?

Build a LangChain agent with the createnetworkslice and deletenetworkslice tools. You can then prompt it to 'provision a high-throughput slice for the drone-fleet device group for 2 hours, then tear it down.' The agent will handle the sequence.

Build fraud detection and network management chains for LangChain agents using live AT&T 5G data.

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 5G MCP to LangChain

Create your Vinkius account to connect AT&T 5G 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 5G with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Smarter Fraud Chains

Your LangChain agent can now build fraud detection logic on the fly. Start a chain with `verify_number` to silently check a user's phone. If that passes, but you need more certainty, the agent can then call `check_sim_swap` to see if there's been recent suspicious activity. It's a multi-step verification process, not a single API call. This isn't just about calling tools; it's about sequencing them. The agent decides what to do next based on the previous step's output. You can trace the whole decision process in LangSmith, seeing exactly why your agent chose to flag an account or let a login proceed. It's security logic that adapts.

Automate Network Slices

Give your LangChain agent the power to manage 5G network slices. A single prompt can trigger a chain that starts with `create_network_slice` for a new IoT deployment. The agent gets the slice ID back and passes it to `get_network_slice_info` to confirm the SLA parameters are correct. When the job is done, another chain can take over. The agent can `list_network_sessions` to ensure no traffic is active, then call `delete_network_slice` to tear it all down. You're not just creating slices; you're building fully automated lifecycle management for your network resources.

QoS Chains for LangChain Agents

Let your agent react to real-world conditions. It can use `get_device_location` to see if a user is in a specific event venue, then proactively call `request_quality_on_demand` with a `high_throughput` profile to ensure smooth video streaming. It's about anticipating user needs, not just reacting to them. These tools become building blocks in your agent's reasoning process. You can build chains that check for roaming status with `check_roaming_status` before requesting QoS, preventing unnecessary charges. This MCP Server gives your agent the context to make smarter, more cost-effective network decisions.

Setup guide

Set up AT&T 5G 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 5G 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-5g-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 5G 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 5G. 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 5G 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 5G MCP in LangChain

Just pass the tools from `client.get_tools()` into your `create_agent` function. The agent will automatically see the function definitions for tools like `verify_number` and `get_device_location` and know when to call them based on your prompt.

Yes, that's the whole point. A chain can call `check_sim_swap` from this MCP server, then use the result to query your own user database through a different integration, all in one sequence.

Build a LangChain agent with the `create_network_slice` and `delete_network_slice` tools. You can then prompt it to 'provision a high-throughput slice for the drone-fleet device group for 2 hours, then tear it down.' The agent will handle the sequence.

Absolutely. If you have LangSmith configured, every call your agent makes to an AT&T 5G tool—like `request_quality_on_demand`—is traced. You'll see the exact inputs, outputs, latency, and token usage for each step.

The server only processes data for the specific tool call, like a phone number for `verify_number`. Vinkius runs each MCP Server in an ephemeral sandbox, so the data is gone after the request is processed. Your LangChain agent just gets the result back.

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