How to Use the AerisWeather MCP in Pydantic AI

Q: How do I set up AerisWeather with Pydantic AI?

Install the library using pip with the mcp extra. Use MCPToolset with your Vinkius HTTP endpoint, and pass it directly into the toolsets argument of your Agent.

Run type-safe weather agents with Pydantic AI and AerisWeather validation at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AerisWeather MCP to Pydantic AI

Create your Vinkius account to connect AerisWeather 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 AerisWeather with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict type validation in Pydantic AI

If an API payload changes, you want your system to fail immediately rather than passing corrupted data to your LLM. This MCP Server integrates with Pydantic AI to validate every weather response against strict Python types. When your agent calls `get_observations` or `get_forecasts`, the incoming data is parsed and verified. If a field is missing or incorrectly formatted, Pydantic AI raises a validation error instantly.

Type-safe geographical lookups on our MCP Server

Finding the right weather station requires clean geographical data. The `get_places` tool returns precise coordinates, city names, and airport codes that your agent can trust. Because Pydantic AI enforces schemas at runtime, your agent will never hallucinate a weather station ID. It resolves the location first, then safely feeds that ID into `get_conditions` to get current weather data.

Efficient batching without silent failures

Running multiple queries can lead to messy, unpredictable payloads. The `get_batch` tool lets your agent fetch forecasts, current conditions, and alerts in one go while maintaining strict type safety. If any of those 31 potential requests in the batch returns unexpected structures, your code catches it before it corrupts your application state. It makes checking `get_alerts` for logistics planning incredibly reliable.

Setup guide

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

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

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

Install the library using pip with the mcp extra. Use `MCPToolset` with your Vinkius HTTP endpoint, and pass it directly into the toolsets argument of your Agent.

Since Pydantic AI validates all tool outputs against strict schemas, your agent cannot invent weather attributes. If it tries to read a non-existent field from `get_forecasts`, the runtime validation stops it.

This integration supports both Streamable HTTP and SSE transports. You just need to ensure the server is hosted externally on Vinkius and pass the correct URL to your toolset.

Yes. Pydantic AI is model-agnostic. You can pair this server with local models, OpenAI, or Anthropic, and the runtime validation rules will still protect your weather data pipelines.

Your requested city names, zip codes, and geographic IDs are processed in memory to fetch the weather. We use ephemeral, zero-trust sandboxes that destroy the session data as soon as the API call completes.

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