Skip to main content
Glama
USDA NASS MCP Server

USDA NASS MCP Server

by kin5

MCP Server for USDA NASS API

The USDA National Agricultural Statistics Service API, known as Quick Stats, contains survey and census data on United States agricultural production.

NASS API access

Request an API key here.

Tools

get_full_dataset(query: Query) -> str

Get all available data for a given commodity, location, and time.

Arguments:

  • query (Query): Dictionary with three keys, "commodity", "location", and "time", each with a dictionary of parameter and value pairs.

Returns:

  • str: Full response text as a string


get_db_record_count(query: Query) -> str

Get the number, or count, of database records of a given commodity for a location and time.

Arguments:

  • query (Query): Dictionary with three keys, "commodity", "location", and "time", each with a dictionary of parameter and value pairs.

Returns:

  • str: String of JSON data with one key, "count", and a value of the number of records.


get_param_values(query: ParameterQuery) -> str

Get all possible values of a query parameter by its name.

Arguments:

  • parameter (ParameterQuery): Dictionary with one key, "param", and a value of the parameter name to get the values for.

Returns:

  • str: String of JSON data with the parameter names and all their possible values as a list.

Related MCP server: USDA MCP Server

Getting started

I highly recommend using uv for package and virtual environment management.

Docker

The Dockerfile is setup to run the MCP server with default settings. Using make, you can build an image and run a container:

  • build: build the image from Dockerfile

  • run: run the MCP server with default settings (e.g. localhost, 8000:8000)

The short way

Setup command

If you have make, uv, and are on macOS/Linux, running make setup should be all you need to get started with the project.

The long way

Installation

Activate your virtual environment and:

pip install -r requirements.txt

.env

Copy the .env.example to a .env file. Replace the value of NASS_API_KEY with your NASS API key.

Configuration

There are several configuration options for changing functionality of the MCP server.

The following configurations are available as environment variables:

Option

Values

Default

Description

NASS_API_KEY

string

Your NASS API key

NASS_MCP_HOST

string

0.0.0.0

The host to run the MCP server on

NASS_MCP_PORT

integer

8000

The port to run the MCP server on

NASS_MCP_FORMAT

CSV or JSON or XML

CSV

The format to return the data in from the NASS API /api_GET endpoint

NASS_ENV

production

A flag for telling the MCP server to skip local dev steps (e.g. load_dotenv)

The following configurations are available as command line arguments

Option

Values

Default

Description

-t --transport

streamable-http or stdio

streamable-http

Transport protocol for the MCP server

Available Tools

3 tools
get_db_record_countB

Get the number, or count, of database records of a given commodity for a location and time.

Args:
    query: Dictionary with three keys, "commodity", "location", and "time", each with a dictionary of parameter and value pairs.

Returns:
    A JSON string containing one key, "count", and a value of the number of records or an error message.

Inputs: query (required). Returns: result

get_full_datasetC

Get all available data for a given commodity, location, and time.

Args:
    query: Dictionary with three keys, "commodity", "location", and "time", each with a dictionary of parameter and value pairs.

Returns:
    A string containing the API response data or an error message.

Inputs: query (required). Returns: result

get_param_valuesB

Get all possible values of a query parameter by its name.

Args:
    parameter: Dictionary with one key, "param", and a value of the parameter name to get the values for.

Returns:
    A JSON string with the parameter name and all possible values as a list or an error message.

Inputs: parameter (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 3 tools

    Disambiguation5/5

    The three tools have clearly distinct purposes: retrieving full data, retrieving only a record count, and discovering parameter values. An agent can easily tell which tool to use for each task.

    Naming Consistency5/5

    All tool names follow a consistent snake_case get_<object> pattern. The naming is predictable and readable across the entire small tool set.

    Tool Count5/5

    Three tools are well within the appropriate range for a focused data-query server, and each tool serves a distinct necessary function. There is no obvious redundancy or padding.

    Completeness4/5

    The surface covers core data retrieval, counting, and parameter-value discovery, but lacks an explicit way to discover parameter names or datasets before querying. This is a minor gap that a knowledgeable agent can work around.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Enables natural language queries of U.S. Census Bureau data, translating plain English questions into proper API calls and returning demographic, economic, and housing statistics with proper statistical interpretation and context.
      3
      20
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables plain English queries about US agricultural data, including historical crop statistics from NASS QuickStats and current cash grain prices from AMS Market News.
      -
    • A
      license
      B
      quality
      B
      maintenance
      Enables AI assistants to query the full FAOSTAT API for global food and agriculture statistics, allowing natural-language questions about crop production, trade, food security, emissions, and more.
      23
      184 PyPI
      20
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables access to USDA Foreign Agricultural Service trade and global production data through MCP, supporting natural language queries and tool-based data retrieval.
      173 npm
      MIT