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

Q: How do my AutoGen agents access the NCEI Climate Data Online (NOAA Archive) tools?

Use the mcpservertools function from the autogen-ext library. It connects to the MCP server and provides the tools in a format that your AssistantAgent can use directly in conversation.

Let AI agents debate climate scenarios using AutoGen. Build multi-agent systems that analyze and interpret NOAA's historical data.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create Agent Teams to Analyze Data

AutoGen lets you build systems where agents converse to solve a problem. Assign one agent to be a "DataFetcher" that uses `get_data` and `search_data`. A second "Analyst" agent can then interpret the results, and a third "Skeptic" agent can use `list_stations` to check for gaps in geographic coverage. This isn't just a simple tool call. It's a structured debate. The agents challenge each other's findings, leading to a more robust conclusion than a single agent could produce on its own. They work together to plan the query sequence.

Delegate Complex Research Tasks

Give your agent group a high-level goal, like "Assess drought risk for our warehouses in Arizona." The agents will figure out the rest. They'll use `list_locations` to find the right area codes, `search_datasets` for relevant datasets like 'Daily Summaries', and `get_data` to pull decades of precipitation records. You're not programming the workflow; you're orchestrating a conversation. The `McpToolAdapter` automatically makes the NOAA tools available to your agents, so they can start their research immediately. This MCP server becomes their window to real-world climate data.

Validate Conclusions with an MCP Server

An agent might propose a theory based on its internal knowledge. You can require it to prove that theory with real data. A "Validator" agent can be tasked to use `get_service_data` to cross-reference the claim against the official NOAA archive, ensuring the final output is grounded in facts. This approach is great for risk assessment. One agent might flag a potential issue, and another can be responsible for digging into the historical record with `list_datatypes` and `get_data` to see if similar events have happened before. The conversation log shows you their entire reasoning process.

Setup guide

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

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes NCEI Climate Data Online (NOAA Archive) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="NCEI Climate Data Online (NOAA Archive)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent NCEI Climate Data Online (NOAA Archive) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="NCEI Climate Data Online (NOAA Archive)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent NCEI Climate Data Online (NOAA Archive) data")
    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 AutoGen

Use the `mcp_server_tools` function from the `autogen-ext` library. It connects to the MCP server and provides the tools in a format that your `AssistantAgent` can use directly in conversation.

Yes. When you configure each agent, you can provide it with a specific subset of the tools. For example, give your research agent `search_data` but restrict your summary agent to only read data provided by others.

A great use case is collaborative analysis. Have one agent pull precipitation data with `get_data`, another pull temperature data, and a third agent synthesize their findings into a single climate risk report.

Yes. The tool execution is part of the agent conversation. You can require human approval before an agent is allowed to execute a costly or long-running tool call, like fetching a decade of data using `get_data`.

The connection is managed by the Vinkius platform, which isolates each session in an ephemeral sandbox. The MCP server only interacts with public NOAA climate data archives, like historical weather observations, and has no access to your code, environment, or other private data.

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