How do I get an OpenWeather API key?

Visit [**openweathermap.org/api**](https://openweathermap.org/api), click **Sign Up** for a free account, go to **API Keys** in your account settings, and create a new key. Copy it — it's a 32-character hex string. Free tier includes 60 calls/minute.

Can I get weather alerts for my location?

Yes! Use `get_weather_alerts` with lat/lon coordinates. Returns active alerts with sender name, event type, severity, description and start/end times. Useful for monitoring severe weather, floods, heat waves and other dangerous conditions.

Can I get historical weather data?

Yes! Use `get_historical_weather` with lat/lon and a date in YYYY-MM-DD format. Returns the weather conditions for that specific day including temperature, humidity, wind and pressure.

How do I find coordinates for a city?

Use `geocode` with the city name (e.g. 'London', 'São Paulo', 'Tokyo'). Returns the top 5 matching locations with their latitude, longitude, country code and state. Use these coordinates with other weather tools.

OpenWeather MCP Server for Pydantic AI 11 tools — connect in under 2 minutes

Name: OpenWeather
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 11 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect OpenWeather through 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 OpenWeather "
            "(11 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in OpenWeather?"
    )
    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 OpenWeather MCP Server

Connect to OpenWeather APIs and access global weather data through natural conversation.

Pydantic AI validates every OpenWeather tool response against typed schemas, catching data inconsistencies at build time. Connect 11 tools through 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

Current Weather — Get real-time temperature, humidity, wind, pressure, visibility and conditions for any location
Hourly Forecast — 48-hour hourly forecast with temperature, precipitation probability and UV index
Daily Forecast — Up to 16-day daily forecast with min/max temperatures and weather descriptions
Weather Alerts — Active severe weather warnings and alerts for any location
Air Quality — Current AQI and 4-day forecast with pollutant concentrations (PM2.5, PM10, O3, NO2, CO)
Historical Weather — Weather conditions for any past date
Sun Times — Sunrise and sunset times for any location
Geocoding — Convert city names to coordinates and vice versa

The OpenWeather MCP Server exposes 11 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 OpenWeather to Pydantic AI via MCP

Follow these steps to integrate the OpenWeather 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 11 tools from OpenWeather with type-safe schemas

Why Use Pydantic AI with the OpenWeather MCP Server

Pydantic AI provides unique advantages when paired with OpenWeather 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 OpenWeather integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your OpenWeather connection logic from agent behavior for testable, maintainable code

OpenWeather + Pydantic AI Use Cases

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

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

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

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

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

OpenWeather MCP Tools for Pydantic AI (11)

These 11 tools become available when you connect OpenWeather to Pydantic AI via MCP:

geocode

Returns the top 5 matching locations with their coordinates, country codes and state names. Use these coordinates with other weather tools. Convert a city name to coordinates

get_air_quality

5, PM10, O3, NO2, SO2, CO, NH3). AQI scale: 1=Good, 2=Fair, 3=Moderate, 4=Poor, 5=Very Poor. Requires lat/lon coordinates. Get current air quality index for a location

get_air_quality_forecast

Each data point includes AQI level (1-5 scale) and concentrations of PM2.5, PM10, O3, NO2, SO2, CO and NH3. Get 4-day air quality forecast for a location

get_current_weather

Requires either city name (e.g. "London", "São Paulo") or latitude/longitude coordinates. Get current weather conditions for a location

get_daily_forecast

Each day includes min/max temperature, humidity, wind, UV index, precipitation probability and weather description. Requires lat/lon coordinates. Get daily weather forecast for up to 16 days

get_forecast

Each data point includes temperature, humidity, wind, pressure and weather description. Optionally set the number of days (1-5). Requires either city name or lat/lon. Get 5-day/3-hour weather forecast

get_historical_weather

Returns temperature, humidity, wind, pressure and weather description for the requested date. Requires lat/lon and date in YYYY-MM-DD format. Get historical weather data for a specific date

get_hourly_forecast

Each hour includes temperature, humidity, wind, UV index, precipitation probability and weather description. Requires lat/lon coordinates. Use geocode to find coordinates for a city name. Get hourly weather forecast using One Call API

get_sun_times

Returns the exact times and the sun's elevation angle at sunrise/sunset. Requires lat/lon coordinates. Get sunrise and sunset times for a location

get_weather_alerts

Returns alert type, severity, description, start and end times. Requires lat/lon coordinates. Useful for monitoring severe weather conditions. Get active weather alerts for a location

reverse_geocode

Returns the city, state, country and postal code for the given coordinates. Convert coordinates to a city name

Example Prompts for OpenWeather in Pydantic AI

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

"What's the current weather in São Paulo?"

"What's the 7-day forecast for Tokyo?"

"Is the air quality good in Beijing right now?"

Troubleshooting OpenWeather MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

OpenWeather + Pydantic AI FAQ

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