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

Q: Can I have one AutoGen agent use the AT&T 5G createnetworkslice tool and another one approve it?

Yes, that's a perfect use case for AutoGen. You'd give the createnetworkslice tool to an "Operator" agent and have a "Manager" agent that reviews the Operator's proposed action before the tool is actually executed.

Q: What about the privacy of phone numbers and location data when my AutoGen agents use the AT&T 5G server?

Data like a phone number for verifynumber or a device ID for getdevicelocation is passed through Vinkius's zero-trust infrastructure. The request is processed in a single-use, sandboxed environment, and no sensitive input data is stored by Vinkius after the fact.

Enable your AutoGen agent teams to debate and execute tasks using AT&T 5G network APIs.

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 AutoGen

Create your Vinkius account to connect AT&T 5G to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Your Agents Debate Slices

This isn't about one agent blindly following orders. Set up an AutoGen team: a "Provisioner" agent wants to use `create_network_slice`, while a "Finance" agent watches the cost. The Provisioner proposes a slice, and the Finance agent can challenge it, asking for justification before giving the go-ahead. Another agent, the "Auditor," can use `get_network_slice_info` to check if the provisioned slice matches the agreed-upon specs. If not, it can flag the discrepancy, triggering a conversation with the Provisioner. The final action is a result of consensus, not a single command.

A Security Team in a Box

Create an AutoGen team to investigate suspicious activity. One agent, the "Detector," gets an alert and uses `check_sim_swap`. It presents its findings: "SIM swapped 2 days ago." A second agent, the "Verifier," then uses `get_device_location` and adds, "And the device is now 1,000 miles away." This MCP server gives them the facts for their debate. A "Human Handoff" agent can then synthesize this conversation and decide if the evidence is strong enough to lock an account or if it needs to escalate. The agents use the AT&T 5G tools to gather evidence and debate the conclusion, leading to fewer false positives.

Agents Negotiate QoS Needs

Imagine a "Gaming" agent and a "Streaming" agent both wanting network resources. The Gaming agent can argue for `low_latency` using `request_quality_on_demand`, while the Streaming agent pushes for `high_throughput`. They can debate priority based on other context, like time of day or user subscription level. A "Manager" agent oversees the conversation, allocates the resource, and confirms the action. It's a dynamic, conversational approach to resource management. Your agents don't just execute tasks; they cooperate and negotiate to use the AT&T 5G network tools effectively.

Setup guide

Set up AT&T 5G MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes AT&T 5G tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="AT&T 5G_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent AT&T 5G data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="AT&T 5G_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent AT&T 5G data")
    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 AutoGen

Yes, that's a perfect use case for AutoGen. You'd give the `create_network_slice` tool to an "Operator" agent and have a "Manager" agent that reviews the Operator's proposed action before the tool is actually executed.

You assign tools to different agents based on their roles. A security agent gets `check_sim_swap`, a network agent gets `request_quality_on_demand`. The agents then discuss the problem, and the one with the right tool for the job proposes a plan to use it.

Absolutely. You can have multiple agents analyze data from the AT&T 5G tools. One agent might flag a `check_sim_swap` result as risky, but another might use `get_device_location` and find the location is normal. They would debate until they agree on whether to raise an alert.

Yes. AutoGen's core feature is showing the conversation between agents. You'll see one agent suggest, "Let's use `request_quality_on_demand` for low latency," and another might reply, "Wait, let's check `check_roaming_status` first to avoid high fees."

Data like a phone number for `verify_number` or a device ID for `get_device_location` is passed through Vinkius's zero-trust infrastructure. The request is processed in a single-use, sandboxed environment, and no sensitive input data is stored by Vinkius after the fact.

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