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` tool 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 tool returns detailed diagnostic results with recommended actions -- helping your field engineers resolve connectivity issues without manual portal navigation.

AT&T IoT MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: AT&T IoT
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect AT&T IoT through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to AT&T IoT "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in AT&T IoT?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About AT&T IoT MCP Server

Connect your AT&T IoT account to any AI agent and take full command of your IoT SIM fleet through natural conversation.

Pydantic AI validates every AT&T IoT tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Device Inventory -- List all IoT SIMs with ICCIDs, statuses (active, suspended, deactivated), data plan names, and last activity dates
Real-Time Status -- Get live connectivity state, IP address, signal strength, data used/remaining, and suspension reasons for any SIM
Activate & Suspend -- Instantly activate suspended devices or suspend compromised SIMs to block network access and contain costs
Resume Devices -- Restore network access to suspended SIMs after troubleshooting or policy clearance without reprovisioning
Data Usage Tracking -- Retrieve current and historical usage per SIM with daily breakdowns, overage alerts, and cycle forecasts
Data Pool Management -- List shared data pools, monitor aggregate consumption, identify top-consuming devices, and prevent pool exhaustion
Device Configuration -- Update rate limits, APN settings, and pool assignments to optimize performance or migrate devices between plans
Automated Diagnostics -- Run connectivity troubleshooting checks including network registration, APN config, data session status, and known outages

The AT&T IoT MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect AT&T IoT to Pydantic AI via MCP

Follow these steps to integrate the AT&T IoT MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from AT&T IoT with type-safe schemas

Why Use Pydantic AI with the AT&T IoT MCP Server

Pydantic AI provides unique advantages when paired with AT&T IoT through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your AT&T IoT integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your AT&T IoT connection logic from agent behavior for testable, maintainable code

AT&T IoT + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the AT&T IoT MCP Server delivers measurable value.

Type-safe data pipelines: query AT&T IoT with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple AT&T IoT tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query AT&T IoT and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock AT&T IoT responses and write comprehensive agent tests

AT&T IoT MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect AT&T IoT to Pydantic AI via MCP:

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

diagnose_connectivity

Returns diagnostic results and recommended actions. Use for rapid troubleshooting of offline devices. Run automated diagnostics to troubleshoot IoT device connectivity

get_data_usage

Use to monitor plan limits, identify heavy users, or forecast billing. Retrieve current and historical data usage for an IoT SIM

get_device_status

Use to troubleshoot offline devices or verify data allowance. Get real-time connectivity and data status of an IoT SIM

get_pool_usage

Use to prevent pool exhaustion or reallocate unused data. Get detailed usage metrics for a specific data pool

list_data_pools

Use to manage enterprise data sharing across fleets. List shared data pools configured for IoT devices

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

resume_device

Use to restore service after troubleshooting or policy clearance. Resume network access for a suspended IoT SIM

suspend_device

Use for lost/stolen devices, cost containment, or decommissioning. Suspend an IoT SIM to block network access

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

Example Prompts for AT&T IoT in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with AT&T IoT immediately.

"List all my IoT devices and show me which ones are suspended."

"Device ICCID 8901234567890123456 is offline. Run diagnostics and tell me what's wrong."

"Check the data pool usage for 'Enterprise-Fleet-A' and tell me our top 5 consuming devices."

Troubleshooting AT&T IoT MCP Server with Pydantic AI

Common issues when connecting AT&T IoT to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

AT&T IoT + Pydantic AI FAQ

Common questions about integrating AT&T IoT MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your AT&T IoT MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.