Does this MCP work with all AI clients?

Yes. You connect this MCP using any AI client that supports the Model Context Protocol (MCP). This means you can use your existing setup in Claude, Cursor, Windsurf, or VS Code.

What kind of data can I get about my devices?

You can get real-time connectivity status, including signal strength and IP addresses. You can also retrieve historical data usage, daily breakdowns, and current data allowance for any SIM.

Can I manage data pools with this MCP?

Absolutely. You can list all shared data pools, monitor aggregate consumption, and identify the top-consuming devices to prevent the pool from running dry.

Is this for technical people only?

No. While the underlying capabilities are technical, the MCP lets you manage the entire process using natural conversation. You don't need to know the API calls; you just need to know what you want to achieve.

What if I need to change a device's settings?

You can update configuration settings like rate limits or APN settings using the MCP. This is useful for optimizing performance or moving devices between different data plans.

What information do I need to identify an IoT SIM?

Each IoT SIM is uniquely identified by its ICCID (Integrated Circuit Card Identifier) -- a 19-20 digit number printed on the SIM card or available in your IoT Control Center dashboard. The ICCID is required for all device-specific operations like activation, suspension, and usage queries. You can list all your devices with list_devices to discover ICCIDs for your entire fleet.

How do data pools work and how can I prevent pool exhaustion?

Data pools are shared data plans across multiple IoT SIMs. Instead of each SIM having an individual cap, all devices in the pool draw from a common data bucket. Use list_data_pools to see your pools, get_pool_usage to check consumption and identify top-consuming devices, and set up alerts before reaching the limit. If a pool is near exhaustion, you can suspend low-priority devices with suspend_device or migrate high-usage devices to a different pool with update_device_settings.

Can I automatically diagnose why an IoT device went offline?

Yes. Use the diagnose_connectivity capability with the device's ICCID. It runs automated checks for network registration status, APN configuration, active data session, signal strength, and known network outages in the device's area. The capability returns detailed diagnostic results with recommended actions -- helping your field engineers resolve connectivity issues without manual portal navigation.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect AT&T IoT to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage every SIM device and data pool from your AI agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through AT&T IoT.

01
Activate device
Returns activation timestamp and assigned IP. Use to onboard new devices or restore service after maintenance. Activate a suspended or deactivated IoT SIM
02
Diagnose connectivity
Returns diagnostic results and recommended actions. Use for rapid troubleshooting of offline devices. Run automated diagnostics to troubleshoot IoT device connectivity
03
Get data usage
Use to monitor plan limits, identify heavy users, or forecast billing. Retrieve current and historical data usage for an IoT SIM
04
Get device status
Use to troubleshoot offline devices or verify data allowance. Get real-time connectivity and data status of an IoT SIM

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through AT&T IoT.

05
Get pool usage
Use to prevent pool exhaustion or reallocate unused data. Get detailed usage metrics for a specific data pool
06
List data pools
Use to manage enterprise data sharing across fleets. List shared data pools configured for IoT devices
07
List devices
Use to audit fleet inventory, identify inactive SIMs, or verify provisioning status. List all IoT SIMs/devices managed in AT&T Control Center

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through AT&T IoT.

08
Resume device
Use to restore service after troubleshooting or policy clearance. Resume network access for a suspended IoT SIM
09
Suspend device
Use for lost/stolen devices, cost containment, or decommissioning. Suspend an IoT SIM to block network access
10
Update device settings
Requires ICCID and JSON settings object. Use to optimize performance or migrate devices between plans. Update configuration settings for an IoT device

Real work

What teams actually run

Handling Lost Equipment

A device is reported stolen. Instead of manually logging in, you ask the AI to suspend the SIM immediately, blocking network access and containing costs.

Diagnosing Offline Units

A remote sensor goes silent. You ask the AI to run diagnostics, which returns the specific issue, like an APN mismatch, and suggests the fix.

Billing Cycle Audits

The finance team needs to know if the current data pool is sustainable. You check the usage and get a forecast of when the pool will hit critical levels.

Onboarding New Devices

A new batch of devices arrives. You use the MCP to activate them and get their initial IP addresses, completing the deployment quickly.

Automate a task

Put AT&T IoT to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

AT&T IoT works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put AT&T IoT to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

892ms average. Fast in production.

AT&T IoT is checked daily against the live service.

Daily averagePeak 1062ms

Oct 3Today

Fastest day: 749ms
Slowest day: 1062ms
14-day trend: Slowing+5%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of AT&T IoT, so you can see the experience inside your AI.

It does not authenticate your account with AT&T IoT. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

AT&T IoT Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_YFstwCIlx1nPc9O3GzBKiwQJk2qplbw9H9PNBDuZ/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — AT&T IoT capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "att-iot-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_YFstwCIlx1nPc9O3GzBKiwQJk2qplbw9H9PNBDuZ/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up AT&T IoT in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work AT&T IoT owners hand off.

This MCP is built for teams that manage large, distributed fleets of connected devices. If your job involves monitoring device health at scale, tracking data consumption, or responding to network failures, this capability replaces manual portal work with conversational commands.

01
IoT Fleet Managers
Monitor device health at scale, track data pool consumption, and prevent SIM exhaustion before it happens.
02
Field Engineers
Diagnose offline devices remotely, activate new deployments, and suspend lost or stolen SIMs instantly.
03
Network Operations
Troubleshoot connectivity issues with automated diagnostics, review APN configurations, and check known outages.
04
Finance Teams
Audit data usage across the fleet, forecast billing cycles, and reallocate unused pool capacity to save costs.

FAQ

Questions AT&T IoT owners ask.

01
Does this MCP work with all AI clients?
Yes. You connect this MCP using any AI client that supports the Model Context Protocol (MCP). This means you can use your existing setup in Claude, Cursor, Windsurf, or VS Code.
02
What kind of data can I get about my devices?
You can get real-time connectivity status, including signal strength and IP addresses. You can also retrieve historical data usage, daily breakdowns, and current data allowance for any SIM.
03
Can I manage data pools with this MCP?
Absolutely. You can list all shared data pools, monitor aggregate consumption, and identify the top-consuming devices to prevent the pool from running dry.
04
Is this for technical people only?
No. While the underlying capabilities are technical, the MCP lets you manage the entire process using natural conversation. You don't need to know the API calls; you just need to know what you want to achieve.
05
What if I need to change a device's settings?
You can update configuration settings like rate limits or APN settings using the MCP. This is useful for optimizing performance or moving devices between different data plans.
06
What information do I need to identify an IoT SIM?
Each IoT SIM is uniquely identified by its ICCID (Integrated Circuit Card Identifier) -- a 19-20 digit number printed on the SIM card or available in your IoT Control Center dashboard. The ICCID is required for all device-specific operations like activation, suspension, and usage queries. You can list all your devices with list_devices to discover ICCIDs for your entire fleet.
07
How do data pools work and how can I prevent pool exhaustion?
Data pools are shared data plans across multiple IoT SIMs. Instead of each SIM having an individual cap, all devices in the pool draw from a common data bucket. Use list_data_pools to see your pools, get_pool_usage to check consumption and identify top-consuming devices, and set up alerts before reaching the limit. If a pool is near exhaustion, you can suspend low-priority devices with suspend_device or migrate high-usage devices to a different pool with update_device_settings.
08
Can I automatically diagnose why an IoT device went offline?
Yes. Use the diagnose_connectivity capability with the device's ICCID. It runs automated checks for network registration status, APN configuration, active data session, signal strength, and known network outages in the device's area. The capability returns detailed diagnostic results with recommended actions -- helping your field engineers resolve connectivity issues without manual portal navigation.

Explore

More in Industry Titans

Connect AT&T IoT to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Activate device

Diagnose connectivity

Get data usage

Get device status

05-07

Get pool usage

List data pools

List devices

08-10

Resume device

Suspend device

Update device settings

What teams actually run

Handling Lost Equipment

Diagnosing Offline Units

Billing Cycle Audits

Onboarding New Devices

Building your own app? The connector is yours to use.

AT&T IoT Connector

Claude Desktop

IoT Fleet Managers

Field Engineers

Network Operations

Finance Teams

Does this MCP work with all AI clients?

What kind of data can I get about my devices?

Can I manage data pools with this MCP?

Is this for technical people only?

What if I need to change a device's settings?

What information do I need to identify an IoT SIM?

How do data pools work and how can I prevent pool exhaustion?

Can I automatically diagnose why an IoT device went offline?

Hologram.io AI Connector

Balena AI Connector

Data Pipeline Prover AI Connector

data.world AI Connector

Suggestions

Hevo Data (ETL & Data Pipeline) AI Connector

AWS IoT Core Device & Limits Calculator AI Connector

Home Network Device Inventory AI Connector

Data.gov Catalog AI Connector