Can my AI read sensor data from my Particle devices?

Yes! Use the `read_variable` tool with your device ID and the variable name (e.g., temperature, humidity, soilMoisture). Your device must expose this variable in its firmware using `Particle.variable()`. The AI will return the current sensor value in real-time. You can find available variables using `get_device_info`.

How do I remotely turn on a pump or actuator connected to a Particle device?

Use the `call_function` tool with your device ID and the function name (e.g., pumpOn, valveOpen). The function must be exposed in your device firmware using `Particle.function()`. You can pass an optional argument (like duration or intensity) to control the actuator behavior. Check available functions with `get_device_info`.

Can I check if my IoT device is online and responding?

Yes! Use the `ping_device` tool to instantly check the online status of any Particle device. You can also use `get_devices` to see the online status of all your devices at once. If a device shows as offline, it may be powered off, disconnected from Wi-Fi, or experiencing firmware issues.

Particle IoT MCP Server for Pydantic AI 8 tools — connect in under 2 minutes

Name: Particle IoT
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 8 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Particle IoT through the 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 Particle IoT "
            "(8 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Particle 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 Particle IoT MCP Server

Connect your Particle IoT API to any AI agent and take full control of your IoT device fleet, sensor monitoring, remote actuator control, and event management through natural conversation.

Pydantic AI validates every Particle IoT tool response against typed schemas, catching data inconsistencies at build time. Connect 8 tools through the 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 Management — List all connected devices, check online status, rename devices, and manage ownership
Sensor Monitoring — Read real-time sensor data from cloud variables (temperature, humidity, soil moisture, etc.)
Remote Control — Execute cloud functions to control actuators, trigger calibrations, and change device modes
Event Publishing — Broadcast custom events to the cloud for logging, alerting, and webhook integration
Health Monitoring — Ping devices to verify connectivity and troubleshoot communication issues
Fleet Overview — Get comprehensive views of your entire IoT deployment and device status

The Particle IoT MCP Server exposes 8 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 Particle IoT to Pydantic AI via MCP

Follow these steps to integrate the Particle 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 8 tools from Particle IoT with type-safe schemas

Why Use Pydantic AI with the Particle IoT MCP Server

Pydantic AI provides unique advantages when paired with Particle 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 Particle 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 Particle IoT connection logic from agent behavior for testable, maintainable code

Particle IoT + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Particle IoT MCP Server delivers measurable value.

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

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

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

Testing and QA: use Pydantic AI's dependency injection to mock Particle IoT responses and write comprehensive agent tests

Particle IoT MCP Tools for Pydantic AI (8)

These 8 tools become available when you connect Particle IoT to Pydantic AI via MCP:

call_function

Functions are defined in the device firmware and can control actuators (turn on pump, open valve), trigger calibrations, change device modes, or perform system tasks. Accepts a single string argument (max 63 characters) to pass to the function. Returns the function execution result code. Essential for remote device control, automation, and actuator management. AI agents should use this when users ask "turn on the water pump on device X", "trigger calibration on sensor Y", or need to remotely control any function exposed by a device. Execute a cloud function on a specific Particle IoT device

get_device_info

Essential for understanding device capabilities before interacting with it. AI agents should reference this when users ask "what variables does device X expose", "what functions can I call on device Y", or need to understand the specific interface of a device. Get detailed information about a specific Particle IoT device

get_devices

Returns device IDs, names, online status, firmware versions, and last connection times. Essential for device inventory management, monitoring connection health, and selecting specific devices for interaction. AI agents should use this when users ask "show me all my devices", "list connected sensors", or need to identify available devices before reading variables or calling functions. List all Particle IoT devices connected to your account

ping_device

Returns current online/offline status and last heard time. Essential for connectivity diagnostics, health monitoring, and verifying device availability before attempting to read variables or call functions. AI agents should reference this when users ask "is device X online", "check connectivity for sensor Y", or need to troubleshoot device communication issues. Check if a specific Particle IoT device is online and responsive

publish_event

Events are broadcast to all subscribed listeners and can be used for inter-device communication, logging, alerting, or triggering external workflows via webhooks. Requires an event name and optional data string (max 255 bytes for data). Essential for sending alerts, logging custom data, and integrating with external systems like IFTTT or custom dashboards. AI agents should use this when users ask "send a low moisture alert", "publish a system status event", or need to broadcast data from the cloud to devices or webhooks. Publish a custom event to the Particle Cloud

read_variable

Variables are defined in the device firmware and can represent sensor readings (temperature, humidity, soil moisture), system status, or configuration values. Returns the variable name, data type, and current value. Essential for real-time sensor monitoring, data collection, and system state verification. AI agents should use this when users ask "what is the temperature from sensor X", "read soil moisture from device Y", or need to get the current value of any sensor or status variable. Read the current value of a cloud variable from a specific device

rename_device

This name appears in the console and API responses, making it easier to identify devices. Essential for device organization, fleet management, and improving readability of device lists. AI agents should use this when users ask "rename device X to Greenhouse Sensor 1", "change the name of device Y to Pump Controller", or need to update device naming for better organization. Rename a specific Particle IoT device

unclaim_device

This action is irreversible for the current account and should be used when transferring device ownership or decommissioning devices. Essential for device lifecycle management, transferring devices, and account cleanup. AI agents should use this when users ask "remove device X from my account", "unclaim sensor Y so I can sell it", or need to manage device ownership. WARNING: This requires confirmation as it removes access to the device. Remove a Particle IoT device from your account

Example Prompts for Particle IoT in Pydantic AI

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

"Show me all my connected Particle devices and their online status."

"Read the current soil moisture from my greenhouse sensor."

"Turn on the irrigation pump for 15 minutes."

Troubleshooting Particle IoT MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Particle IoT + Pydantic AI FAQ

Common questions about integrating Particle 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 Particle IoT MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.