How to Use the NCDC Climate Data Online MCP in Pydantic AI

Q: How do I register the NCDC Climate Data Online toolset in pydantic-ai?

Install the package using pip install "pydantic-ai-slimmcp". Use the unified MCPToolset class with your Vinkius HTTP URL, and pass it to your Agent via the toolsets parameter.

Q: Does pydantic-ai validate the schemas of NCDC Climate Data Online tools?

Yes. Every tool call, from listdatacategories to getclimatedata, is validated against strict Pydantic models at runtime to prevent malformed queries or responses.

Type-safe historical weather data ingestion using pydantic-ai and MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NCDC Climate Data Online MCP to Pydantic AI

Create your Vinkius account to connect NCDC Climate Data Online 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 NCDC Climate Data Online with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict type validation for the NCDC Climate Data Online MCP Server.

The `get_climate_data` tool outputs raw weather records that pydantic-ai validates against strict Python types at runtime. Weather data can be messy, with missing values or weird schemas. Pydantic AI forces every response to validate, catching anomalies instantly. Your pydantic-ai agent uses `list_data_types` and `get_station` to explore the climate database safely. Because every tool output is validated, you never have to worry about silent data corruption breaking your downstream climate models.

Build model-agnostic weather agents.

Using `list_datasets` with pydantic-ai lets you build model-agnostic agents that query climate databases safely. The framework handles the tool translation, letting your agent run `list_datasets` and `get_dataset` regardless of the model backend. This flexibility is crucial when testing how different models reason about historical weather patterns. You can swap the underlying model in one line of code while keeping your `get_climate_data` validation logic completely intact.

Eliminate silent failures in weather queries.

Querying weather stations with `list_stations` can sometimes return missing fields, which pydantic-ai catches instantly. Standard agents might hallucinate missing fields, but Pydantic AI raises a loud validation error the second the schema deviates. It forces the pydantic-ai agent to handle the error programmatically, perhaps by falling back to `list_locations` to find an alternative station. This guarantees that only clean, well-formed climate records pass through your pipeline.

Setup guide

Set up NCDC Climate Data Online 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": {
        "ncdc-climate-data-online-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent NCDC Climate Data Online 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 NCDC Climate Data Online. 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 NCDC Climate Data Online 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 NCDC Climate Data Online MCP in Pydantic AI

Install the package using pip install "pydantic-ai-slim[mcp]". Use the unified MCPToolset class with your Vinkius HTTP URL, and pass it to your Agent via the toolsets parameter.

Yes. Every tool call, from list_data_categories to get_climate_data, is validated against strict Pydantic models at runtime to prevent malformed queries or responses.

No. You should use the unified MCPToolset class instead. It handles the connection to the external MCP Server more reliably and supports both HTTP and SSE.

Pydantic AI will validate the response against the expected schema. If a null value is returned where a float is expected, it raises a validation error so your code can handle it.

All requests flow through a secure, ephemeral V8 isolate sandbox on Vinkius. Your station queries and weather records are processed in memory and never stored, keeping your environmental data private.

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