How to Use the AirVisual MCP in Pydantic AI

Q: How do I configure AirVisual for Pydantic AI?

Install the pydantic-ai-slimmcp package. Create a toolset using your Vinkius HTTP endpoint, and pass it into your Agent's toolsets parameter.

Q: What happens if AirVisual returns unexpected data to Pydantic AI?

The framework immediately throws a validation error. If getcitydata returns a string where your model expects an integer for the AQI, the agent stops execution entirely.

Strictly validate AirVisual meteorological data in Pydantic AI. Catch hallucinated AQI metrics before they hit your application logic.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AirVisual MCP to Pydantic AI

Create your Vinkius account to connect AirVisual 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 AirVisual with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe weather lookups in Pydantic AI

Silent data corruption ruins production systems. When your agent calls `get_city_data`, this framework validates the returned AQI and pollution levels against your strict Pydantic models at runtime. If the underlying API changes its response format, your agent fails loudly. You get a clear validation error instead of passing malformed meteorological data from the MCP Server into your downstream database.

Validate coordinate and IP routing

Location resolution needs exact typing. Your agent executes `get_nearest_city_by_coords` or `get_nearest_city_by_ip` to find local conditions, and the framework ensures the resulting geographic coordinates match your schema. You configure the MCP Toolset using the unified HTTP approach. This connects your model-agnostic agent to the external endpoints, letting you swap between OpenAI and local models without rewriting the tool definitions.

Traverse geographical data safely

Agents notoriously hallucinate city and state names. You prevent this by forcing the agent to query `list_countries`, `list_states`, and `list_cities` before it ever attempts a station lookup. Every step of that hierarchy gets validated. When the agent finally calls `get_station_data`, you know the input parameters are valid and the returned sensor readings will exactly match your expected types.

Setup guide

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

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

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

Install the `pydantic-ai-slim[mcp]` package. Create a toolset using your Vinkius HTTP endpoint, and pass it into your Agent's `toolsets` parameter.

The framework immediately throws a validation error. If `get_city_data` returns a string where your model expects an integer for the AQI, the agent stops execution entirely.

Yes, the framework is completely model-agnostic. Your local LLM can call `get_station_data` through the exact same MCP Server configuration as a proprietary model.

Guessing leads to failed API calls. Forcing your agent to execute `list_states` and `list_cities` guarantees it only requests weather data for supported AirVisual locations.

Every request runs inside an ephemeral V8 Isolate. Once your agent receives the AQI data for a specific IP address or coordinate pair, the sandbox terminates and all trace of the request vanishes.

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