USDA MCP Server

MCP server that connects USDA's NASS QuickStats and AMS Market News APIs to any MCP-compatible AI model, allowing farmers, researchers, and USDA staff to ask plain English questions about US agricultural data and get accurate, data-backed answers.

Built for the Challenge X Hackathon — Feb 28 to Apr 18, 2026. Team: Root Access

What This Does

Farmers, researchers, and USDA staff can ask plain English questions about US agricultural data and get accurate, data-backed answers — without needing to know what an API is or how to find the data themselves.

Historical data (NASS QuickStats)

• "What was the corn yield in Iowa in 2022?"

• "How has soybean production in Illinois trended from 2018 to 2022?"

• "How many acres of wheat were planted in Kansas in 2021?"

• "What price did Iowa farmers receive for corn in 2022?"

• "What was national corn production in 2022?"

Current market prices (AMS Market News)

• "What is the current corn price in Iowa?"

• "What is today's soybean price in Illinois?"

• "Where should I sell my soybeans — iowa, illinois, or nebraska?"

• "What is the current wheat price in Kansas?"

Tools

The server exposes 4 MCP tools:

Project Structure

usda-mcp/
├── clients/
│   ├── nass_client.py       # NASS QuickStats API wrapper
│   └── ams_client.py        # AMS Market News API wrapper
├── server/
│   ├── main.py              # MCP server — 4 tools
│   ├── security.py          # OWASP MCP Top 10 mitigations
│   └── tools/
│       └── __init__.py
├── tests/
│   └── qa_log.csv           # Q&A evaluation log
├── demo/
│   └── app.py               # Demo interface (planned)
├── logs/
│   └── usda_nass_server.log # Auto-generated server log
├── .env                     # API keys (never committed)
├── .env.example             # Template for API keys
├── requirements.txt         # Pinned dependencies
├── SECURITY.md              # OWASP MCP Top 10 documentation
└── README.md

Setup

1. Clone the repo

git clone https://github.com/RolakeOkans/usda-mcp.git
cd usda-mcp

2. Create a virtual environment

python -m venv .venv
source .venv/bin/activate

3. Install dependencies

pip install -r requirements.txt

4. Create a .env file in the root folder

NASS_API_KEY=your_nass_key_here
AMS_API_KEY=your_ams_key_here

5. Get your API keys

NASS: Register at https://www.nass.usda.gov/developer/index.php

AMS: Register at https://mymarketnews.ams.usda.gov

Both are free and issued within minutes.

Connect to Claude Desktop

Add this to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "usda-nass": {
      "command": "/path/to/your/python",
      "args": ["/path/to/usda-mcp/server/main.py"],
      "env": {
        "NASS_API_KEY": "your_key_here",
        "AMS_API_KEY": "your_key_here"
      }
    }
  }
}

Replace paths with your actual Python and project paths.

Verified Data — NASS QuickStats

All queries tested and confirmed working for Iowa, 2022.

Verified Data — AMS Market News

Current prices confirmed working as of April 2, 2026.

Data Sources

How It Works

User asks a plain English question
        ↓
AI model reads the question and decides which tool to call
        ↓
MCP server validates and sanitizes the input
        ↓
NASS or AMS API returns the raw data
        ↓
Server scans response for security issues
        ↓
AI model interprets the data and returns a plain English answer
        ↓
All tool calls logged to logs/usda_nass_server.log

Security

This server addresses all 10 OWASP MCP Top 10 risks. See SECURITY.md for full details.

Summary:

• API keys stored in .env, never committed, redacted from all logs

• Read-only server — GET requests only, no write access to any USDA system

• Input sanitization on all tool arguments

• Rate limiting at 30 requests per minute per tool

• Prompt injection detection on all API responses

• Full audit logging of every tool call

Never commit your .env file. It is listed in .gitignore.

Team — Root Access

Hackathon

Challenge X+ USDA Timeline: Feb 28 to Apr 18, 2026 Showcase: April 18, 2026