How do I get weather for a specific city?

First use `search_location` with the city name (e.g. 'Tokyo') to find its AccuWeather location key. Then use that key with `get_current_conditions` for current weather, `get_daily_forecast` for the forecast, or `get_hourly_forecast` for hour-by-hour details.

What's the difference between daily and hourly forecasts?

Daily forecasts (1-15 days) give you one summary per day with high/low temperatures and overall conditions. Hourly forecasts (12-120 hours) give you weather for each individual hour — perfect for knowing exactly when rain will start, when temperatures peak, or the best time for outdoor activities. Use hourly for precise timing, daily for general planning.

Can I get severe weather alerts?

Yes. Use the `get_weather_alarms` tool with a location key to check for active severe weather alerts. This includes hurricanes, tornadoes, flood warnings, heat advisories, winter storm warnings, and more. Returns empty if no active alarms. Essential for emergency preparedness and travel safety decisions.

AccuWeather MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: AccuWeather
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

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

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

Access AccuWeather's superior weather forecasting — the industry standard used by enterprises worldwide for accurate, localized weather data. Connect AccuWeather to your AI agent to get current conditions, daily and hourly forecasts, severe weather alarms, and activity planning indices for any location on Earth — all through natural conversation.

Pydantic AI validates every AccuWeather tool response against typed schemas, catching data inconsistencies at build time. Connect 10 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 Conditions — Get real-time temperature, RealFeel, humidity, wind, UV index, and visibility for any city.
Daily Forecasts — Retrieve 1 to 15-day forecasts with high/low temperatures, precipitation probability, and sunrise/sunset times.
Hourly Forecasts — Get hour-by-hour weather for up to 120 hours (5 days) for precise planning.
Weather Alarms — Monitor active severe weather alerts including hurricanes, tornadoes, floods, and heat advisories.
Activity Indices — Get recommendations for outdoor activities, UV exposure, running, golf, fishing, and more.
Location Search — Find any city, town, or place worldwide and get its weather.
Metric Units — All data returned in Celsius, km/h, and kilometers for international use.

The AccuWeather MCP Server exposes 10 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 AccuWeather to Pydantic AI via MCP

Follow these steps to integrate the AccuWeather 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 10 tools from AccuWeather with type-safe schemas

Why Use Pydantic AI with the AccuWeather MCP Server

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

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

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

AccuWeather + Pydantic AI Use Cases

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

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

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

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

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

AccuWeather MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect AccuWeather to Pydantic AI via MCP:

get_current_conditions

Returns temperature (metric), weather text (e.g. "Partly sunny"), RealFeel temperature, humidity, wind speed and direction, UV index, visibility, cloud cover, and precipitation. Essential for instant weather checks. Use get_location_by_key first to find the correct location key. Get current weather conditions for a location

get_current_conditions_metric

Returns temperature in Celsius, wind in km/h, visibility in kilometers. Includes RealFeel temperature, humidity, UV index, wind gusts, and precipitation data. Use for international audiences or scientific analysis. Get current weather conditions with detailed metric values

get_daily_forecast

Each day includes high and low temperatures, weather conditions, precipitation probability, wind speed, UV index, sunrise/sunset times, and air quality information. Returns data in metric units (Celsius, km/h). Essential for trip planning, event scheduling, and agricultural decisions. Use 5 days for standard weekly forecasts. Get daily weather forecast for a location

get_extended_forecast

While forecasts beyond 7-10 days have lower accuracy, this is useful for event planning, travel preparation, and agricultural scheduling. Each day includes high/low temperatures, precipitation probability, and general conditions. Use for planning events 2 weeks in advance. Get 15-day extended weather forecast

get_hourly_forecast

Each hour includes temperature, weather icon, precipitation probability, wind speed and direction, and cloud cover. Essential for detailed planning — knowing exactly when rain will start, when temperatures peak, or when conditions are safe for outdoor activities. Returns data in metric units. Use 24 hours for tomorrow planning. Get hourly weather forecast for a location

get_index_groups

This helps you understand what types of indices are available (outdoor activities, health, home & garden, etc.) before querying specific indices for a location. Use this to discover what activity planning indices are supported. Get available index groups and categories

get_location_by_key

Returns the city name, country, region, timezone, coordinates, elevation, and administrative area. Use this to verify you have the correct location before making weather queries. Get detailed information about a location by its AccuWeather key

get_weather_alarms

Includes severe weather alerts such as hurricanes, tornadoes, flood warnings, heat advisories, and winter storm warnings. Each alarm includes severity level, description, start and end times, and source. Essential for safety planning, emergency preparedness, and travel decisions. Returns empty if no active alarms. Get active weather alarms and warnings for a location

get_weather_indices

Includes indices for outdoor activity suitability, flight delay probability, UV exposure, running, hiking, golf, fishing, lawn mowing, composting, and more. Each index includes a numeric value, category (e.g. "Excellent", "Poor", "Good"), and descriptive text. Essential for activity planning, health advisories, and lifestyle decisions. Get weather indices (outdoor activity, flight, UV, etc.) for a location

search_location

The location key is required for other weather queries. Returns matching locations with their keys, country, region, and coordinates. Use this as the first step before any weather query. For example, search for "New York" to find the correct location key for New York City. Supports partial matching and returns multiple results. Search for a location by name to get its AccuWeather location key

Example Prompts for AccuWeather in Pydantic AI

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

"What's the weather like in Tokyo right now?"

"Give me the 5-day forecast for Paris, France."

"Are there any severe weather alerts for Miami right now?"

Troubleshooting AccuWeather MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

AccuWeather + Pydantic AI FAQ

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