How to Use the Tomorrow.io Extended MCP in Pydantic AI

Build reliable agents with Pydantic AI that validate every Tomorrow.io Extended response.

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 Extended MCP to Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get air quality data via `get_air_quality`

When the agent calls `get_air_quality`, you get a structured, validated JSON object back. If the underlying API sends unexpected pollutant values, your agent fails immediately with an error. This means no silent corruption of data. You know exactly when the source data breaks down.

Retrieve past conditions using `get_recent_history`

Use `get_recent_history` to pull back weather logs. Pydantic ensures that every field—like 'dew point' or 'barometric pressure'—matches the expected type before your agent can use it. This level of validation means you rely on correct data, not just available data.

Check for current warnings with `list_weather_alerts`

The agent executes `list_weather_alerts`, and the result is instantly validated against your schema. You don't have to worry about mismatched field names or missing required data. It’s all about correctness first. The framework catches bad API responses before they ever reach your application logic.

Setup guide

Set up Tomorrow.io Extended 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-extended-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 Extended tools.",
)

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

Every response from the MCP Server is validated against a defined Python model at runtime. If `get_weather_forecast` returns an unexpected structure, your agent throws a loud validation error, stopping execution safely.

Yes. Because it forces type safety, you gain confidence that when the agent calls `get_realtime_weather`, the data structure is exactly what your code expects, eliminating guesswork.

You define your desired output schema and pass it to the MCPToolset. When you run an agent action, like getting air quality data, the toolset validates the response against that structure.

Yes, since it’s model-agnostic, you can connect your MCP Server calls whether your backend uses OpenAI, Gemini, Anthropic, or a self-hosted model.

The server provides environmental readings and atmospheric metrics. The validation layer ensures that values like wind speed (float) or alert status (boolean) are always correctly typed.

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