How to Use the NCEI Climate Data Online (NOAA Archive) MCP in Pydantic AI

Q: How do I initialize the NCEI Climate Data Online (NOAA Archive) in Pydantic AI?

Install pydantic-ai-slimmcp and use the unified MCPToolset class pointing to your server's HTTP endpoint. Pass the resulting toolset into your Agent constructor. The older MCPServerHTTP method is deprecated.

Q: What models can I use to query this weather data?

The framework is completely model-agnostic. You can route searchdata and liststations outputs through Anthropic, OpenAI, Gemini, or even a local Llama model depending on your latency requirements.

Q: Can I use the NCEI Climate Data Online (NOAA Archive) to find specific hardware platforms in Pydantic AI?

Yes. The liststations tool returns the observing platforms for a given area. Your agent parses the JSON response, validates the station IDs against your schema, and uses them for localized weather queries.

Build type-safe climate pipelines by connecting the NCEI Climate Data Online (NOAA Archive) to 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 NCEI Climate Data Online (NOAA Archive) MCP to Pydantic AI

Create your Vinkius account to connect NCEI Climate Data Online (NOAA Archive) 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 NCEI Climate Data Online (NOAA Archive) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Climate Data Ingestion

The `get_data` tool retrieves historical observations that Pydantic AI instantly validates against your predefined schemas. If the NOAA API returns a missing temperature value or an unexpected string format, the framework fails loudly. You never have to worry about silent corruption ruining your downstream climate models. Discovering available metrics requires precision. Your agent uses `list_datatypes` and `list_datacategories` to pull exact variable codes like PRCP or TAVG. Because every response is strictly typed, the agent knows exactly which string literals to pass into subsequent retrieval tools.

Geospatial Querying with the MCP Server

The `list_locations` and `list_locationcategories` tools allow your agent to resolve geopolitical entities into valid identifiers. It queries states, countries, or bounding boxes, ensuring the search parameters match the API's strict formatting rules. Pydantic models catch any malformed coordinates before the request even leaves your server. Hardware mapping relies on the `list_stations` endpoint to function. The agent pulls the metadata for weather observing platforms and validates their operational status. You get a clean, validated list of sensor IDs to feed into your localized risk assessment pipelines.

Strict Dataset Resolution

The `list_datasets` and `search_datasets` tools search the archive for specific temporal resolutions like Daily Summaries. Your agent reads the catalog and confirms the dataset exists before attempting to pull records. This strict verification step prevents the agent from hallucinating dataset names. Advanced filtering happens through the `search_data` tool. The agent applies spatial and temporal bounds to discover exact climate records. Since the API enforces a 1-year limit on daily data and a 10-year limit on monthly data, you can write Pydantic validators that block your agent from requesting invalid date ranges entirely.

Setup guide

Set up NCEI Climate Data Online (NOAA Archive) 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": {
        "ncei-climate-data-online-noaa-archive-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent NCEI Climate Data Online (NOAA Archive) 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 NOAA NCEI. 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 NCEI Climate Data Online (NOAA Archive) 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 NCEI Climate Data Online (NOAA Archive) MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` and use the unified `MCPToolset` class pointing to your server's HTTP endpoint. Pass the resulting toolset into your Agent constructor. The older `MCPServerHTTP` method is deprecated.

You can write custom validators to enforce the API's strict date rules. If an agent tries to pass a 5-year date range to `get_data` for a daily dataset, your Pydantic model intercepts it and throws a validation error before the HTTP request fires.

The framework is completely model-agnostic. You can route `search_data` and `list_stations` outputs through Anthropic, OpenAI, Gemini, or even a local Llama model depending on your latency requirements.

Yes. The `list_stations` tool returns the observing platforms for a given area. Your agent parses the JSON response, validates the station IDs against your schema, and uses them for localized weather queries.

Not at all. The server merely executes GET requests for public meteorological observations, bounding areas, and dataset categories. It completely isolates your Pydantic AI schemas, internal prompts, and user queries from the external government endpoint.

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