How to Use the Particle IoT MCP in Pydantic AI

Bring type-safe hardware control to Pydantic AI with this Particle IoT MCP Server for reliable, validated device interactions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Particle IoT MCP to Pydantic AI

Create your Vinkius account to connect Particle IoT to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Particle IoT with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-safe device control in Pydantic AI

Every command sent via `call_function` is validated against your Pydantic models. If the firmware returns malformed data, your agent stops immediately. This prevents silent failures in your hardware logic. You get strict, runtime verification that your device state matches your expected schema.

Validated sensor monitoring with Pydantic AI

Retrieve sensor values using `read_variable` and verify them against your models. The agent rejects any response that deviates from your defined types. This ensures your agent only acts on accurate, structured data. You can trust the input from your sensors because the server enforces strict data contracts.

Managed fleet operations via MCP Server

List and organize your hardware with `get_devices`. The tool outputs structured device objects that Pydantic AI processes natively. This makes fleet-wide monitoring predictable and safe. You can rename or unclaim devices with the confidence that the API interaction is fully typed.

Setup guide

Set up Particle IoT MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "particle-iot-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Particle IoT tools.",
)

result = await agent.run("List recent Particle IoT transactions")
print(result.output)

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 Particle IoT. 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.