How to Use the USDA NASS MCP in LangChain

Build multi-step USDA NASS data pipelines using LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect USDA NASS MCP to LangChain

Create your Vinkius account to connect USDA NASS 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 USDA NASS with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Step Data Processing with MCP Server

You can build complex reasoning chains that pull agricultural insights from the USDA NASS MCP Server. Start by running `get_param_values` to check valid filters, then use those results to feed a targeted query into `get_quick_stats`. This lets your agent decide exactly which data points it needs and in what sequence. For instance, you might first call `search_by_commodity` for 'WHEAT' to get an overview. Then, depending on the initial results, you can branch out and run `get_crop_summary` to drill down into state-specific yield data without needing a new prompt.

Deep Dive into Crop Yields via LangChain

The `get_crop_summary` tool gives you detailed statistics for any commodity, like SOYBEANS or COTTON. It requires the commodity name and lets you optionally narrow results by state and year. This means your chain can dynamically generate reports comparing yields across different regions over time. You won't just get a number; you'll get full context—units, geographic scope, and time period included in the output. Your agent uses this structure to build out final reports that aren't just single API calls.

Connecting Economics and Demographics with MCP Server

`get_economics_data` pulls agricultural economics data, while `get_demographics_data` handles population statistics. Both tools let you filter by state and year, letting your agent compare economic trends against demographic shifts. For example, check how the profitability of HOGS production correlates with local population density. Your LangChain script treats these as two separate inputs that need to be joined in a single outcome. This capability lets you build sophisticated models that require multiple, distinct data sources.

Setup guide

Set up USDA NASS 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 USDA NASS 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({
    "usda-nass-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 USDA NASS 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 USDA NASS. 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 USDA NASS 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 USDA NASS MCP in LangChain

You set up an agent to call the MCP Server. The agent decides which tool—like `get_crop_summary` or `search_by_commodity`—to run first based on your prompt. It then uses the output of that initial call as context for its next decision.

You're accessing everything from crop yields (like CORN) to livestock summaries (CATTLE). The server provides economic, demographic, and production statistics across various sectors.

Absolutely. You can chain together calls. For example, you might pull demographics first, then use the resulting states to run a specialized `get_livestock_summary` for that area.

Yes. Most tools accept an optional year filter, giving you historical data. You can compare 2021 yields to 2023 yields in a single chain run.

The server touches agricultural statistics: commodity names, state filters, and years. These are the primary inputs for all its tools.

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