How to Use the AQICN MCP in Pydantic AI

Validated air quality data for your type-safe Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AQICN MCP to Pydantic AI

Create your Vinkius account to connect AQICN to Pydantic AI 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 AQICN with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict type-checking for AQICN in Pydantic AI

Every response from `get_city_feed` is validated against your Pydantic models. If the data structure changes, the agent stops before processing bad info. This protects your agent from silent failures. You get clean, typed data in every turn.

Search and validate stations using Pydantic AI

Run `search_stations` to find valid monitoring sites while ensuring the output matches your schema. Pydantic AI verifies the station list at runtime. This removes the risk of hallucinated station UIDs. You only work with confirmed data points.

Reliable air quality feeds for Pydantic AI

The `get_ip_feed` tool provides real-time data that your agent casts into a rigid model. It fails loudly if the feed returns unexpected fields. This is the safest way to handle external environmental data. Your logic stays sound because your inputs are guaranteed.

Setup guide

Set up AQICN 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": {
        "aqicn-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent AQICN 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 AQICN. 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 AQICN 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 AQICN MCP in Pydantic AI

Install the pydantic-ai-slim package and initialize the MCPToolset with your server URL. The agent then validates every tool call automatically.

Only when the data is malformed. This is a feature, not a bug, ensuring your agent never acts on corrupted air quality readings.

The server uses a zero-trust sandbox. Your specific location or station queries are never stored or logged long-term.

Yes. The server supports both Streamable HTTP and SSE, allowing you to choose the transport that fits your deployment.

It is model-agnostic. Whether you use OpenAI, Anthropic, or local models, the type-safety remains consistent across the board.

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

Mastra AI sdk-typescript

Start using the AQICN MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started