How to Use the Tomorrow.io MCP in Pydantic AI

Q: How does Tomorrow.io integrate with Pydantic AI?

When using the MCP Server, every response from a tool like gethourlyforecast is validated by Pydantic models at runtime. This means if the API returns junk data, your agent fails loudly instead of running on bad info.

Q: Can tomorrowio-mcp predict pollen counts using Pydantic AI?

Yes. The getpollenforecast tool retrieves daily pollen count indices. Because of the schema validation, you'll get a clean data type for that count every time.

Q: Does Tomorrow.io support custom query ranges with Pydantic AI?

It does. The getcustomtimelines tool lets your agent precisely define the start and end points of a weather data retrieval, making sure the output fits your required schema.

Build correct weather agents with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Tomorrow.io MCP to Pydantic AI

Create your Vinkius account to connect Tomorrow.io 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 Tomorrow.io with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

MCP Server: Getting Current Location Data

You can get the most current data using `get_realtime_weather`, supplying a location via city name, zip code, or coordinates. This tool is critical for immediate agent action. If your model needs to know about risks, it pulls specialized reports like `get_wildfire_risk` or general road hazards through `get_road_weather_risk`. Every field returned validates against the Pydantic schema.

Forecasting Weather Events with Pydantic AI

The system provides forecasts over various timeframes. You can use `get_daily_forecast` for 15-day outlooks or `get_hourly_forecast` for detailed, hour-by-hour predictions. Both return structured data. Don't forget the historical context. `get_historical_weather` fetches actual recorded observations, allowing your agent to compare modeled output against known facts.

Advanced Climate Data Retrieval via MCP Server

Need precision? You can pull minute-by-minute rainfall data using `get_minutely_precipitation`. For broader planning, the `get_air_quality_index` gives immediate environmental status. The server also handles niche data like pollen counts (`get_pollen_forecast`) and allows you to tailor your queries with `get_custom_timelines`, ensuring your agent only gets what it needs.

Setup guide

Set up Tomorrow.io 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": {
        "tomorrowio-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

When using the MCP Server, every response from a tool like `get_hourly_forecast` is validated by Pydantic models at runtime. This means if the API returns junk data, your agent fails loudly instead of running on bad info.

It supplies highly structured weather metrics, including air quality indices, current real-time conditions, and specific risk assessments like wildfire danger levels.

Yes. The `get_pollen_forecast` tool retrieves daily pollen count indices. Because of the schema validation, you'll get a clean data type for that count every time.

It does. The `get_custom_timelines` tool lets your agent precisely define the start and end points of a weather data retrieval, making sure the output fits your required schema.

The MCP Server touches several critical types: air quality index measurements, precipitation amounts (minute-by-minute), and historical weather observations.

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