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

Q: How do I create a chain with LangChain and the NCEI Climate Data Online (NOAA Archive) tools?

Get the tools with client.gettools() and pass them to a LangChain agent constructor, like createagent. The agent can then chain calls, like using searchdatasets to find a dataset ID for getdata.

Build agents that reason over historical climate data with LangChain. Chain tools to find, filter, and fetch NOAA records.

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 LangChain

Create your Vinkius account to connect NCEI Climate Data Online (NOAA Archive) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Climate Queries Together

Start by finding relevant datasets with `search_datasets`. Then, use that output to automatically `list_stations` in the area. Finally, pull the numbers you need with `get_data` for a specific time range. LangChain makes this a single, logical flow. Your agent decides the next step, it's not a fixed script. If `list_stations` returns nothing, the agent can backtrack and try a different area from `list_locations` without you coding every edge case. That's the point of autonomous chains.

Ground Your Agents in Hard Data

Stop agents from making things up about the weather. These tools connect directly to the official NOAA archive. Your agent can use `list_datatypes` to see exactly what's available—like `TAVG` (average temperature) or `PRCP` (precipitation)—and then request it. LangSmith tracing gives you a clear view of every tool call from this MCP server. You see the inputs, the raw JSON output, and how long it took. It's full observability for debugging your climate models.

Build Custom Climate Tools with this MCP Server

The ten tools are your building blocks. A ReAct agent can combine `list_locationcategories` and `list_locations` to explore what geographic data is available before committing to a deep query. It's about giving the agent enough context to make smart choices. This MCP server handles the connection and authentication to the NOAA API. You just give your agent the tools from `client.get_tools()`. It's a faster way to get a climate-aware agent working inside your existing LangChain projects.

Setup guide

Set up NCEI Climate Data Online (NOAA Archive) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes NCEI Climate Data Online (NOAA Archive) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "ncei-climate-data-online-noaa-archive-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent NCEI Climate Data Online (NOAA Archive) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Get the tools with `client.get_tools()` and pass them to a LangChain agent constructor, like `create_agent`. The agent can then chain calls, like using `search_datasets` to find a dataset ID for `get_data`.

Yes. If you have LangSmith configured, every tool call from this MCP server is traced automatically. You'll see the exact inputs and outputs for tools like `list_stations` and `get_data`.

The server has rate limits, so design your chains to be efficient. Use `search_data` to narrow your query before pulling a full year of daily summaries with `get_data` to avoid hitting API limits.

It can be. This MCP server gives your LangChain agent direct, structured access to the NOAA archive without you writing the API client code. It's faster to get started.

Your Vinkius token authenticates you to the MCP server, so your raw NOAA credentials are never exposed. The server only processes requests for historical climate data like precipitation and temperature records; it doesn't access any of your personal or proprietary information.

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