usdc-arc-mcp-demo

GSA-TTS/usdc-arc-mcp-demo

3.3

If you are the rightful owner of usdc-arc-mcp-demo and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

This is a proof of concept MCP server for analytics.usa.gov data, showcasing LLM interaction with government analytics APIs.

Tools
3
Resources
0
Prompts
0

analytics.usa.gov MCP Server

⚠️ DISCLAIMER: This is a proof of concept and is not intended for production use.

Demo MCP Server for AI Community Of Practice

Overview

This project is a demonstration Model Context Protocol (MCP) server for analytics.usa.gov data, designed to showcase how LLMs can interact with government analytics APIs using the MCP standard. The codebase is structured to start simple and build up in capability:

  • single_report_tool: Provides basic access to a single analytics report at a time, ideal for simple queries and initial integration.
  • multiple_reports_tools: Adds support for fetching and handling multiple reports, allowing more complex queries and comparisons.
  • aggregation_tools: Enables aggregation of analytics data over time periods (week, month, year) and by various dimensions (such as source or agency), supporting more advanced analytics and summarization.

Each tool is registered with the MCP server and can be called by an LLM or other MCP-compatible client. The project is intended as a learning and experimentation platform for building and extending MCP-based analytics APIs.

Quick Start (Recommended)

Option 1: Install via uv

uv tool install git+https://github.com/GSA-TTS/usdc-arc-mcp-demo/

This will install the MCP server as a CLI tool. You can then run:

usdc-arc-mcp-demo
Simple way to connect to Claude

  1. Get the installed tool path:

    which usdc-arc-mcp-demo

  2. Copy the path into Claude MCP config:

    {
  "mcpServers": {
    "usdc-arc-mcp-demo": {
      "command": "/path/to/usdc-arc-mcp-demo",
      "args": [],
      "env": {
         "DAP_API_KEY": "your-api-key"
      }
    }
  }
}

Development Setup

Option 2: Using Hatch or uv

Using Hatch
  1. Install Hatch: 
    pip install hatch
  2. Create a virtual environment and install dependencies: 
    hatch env create
  3. Run the server: 
    hatch run usdc-arc-mcp-demo
    Or: 
    hatch shell

usdc-arc-mcp-demo


#### Using uv

1. Install [uv](https://github.com/astral-sh/uv):
```sh
pip install uv
  1. Install dependencies: 
    uv pip install -r requirements.txt
    Or, for PEP 621 projects: 
    uv pip install -e .
  2. Run the server: 
    usdc-arc-mcp-demo

Configuration

Set your Regulations.gov API key in a .env file:

DAP_API_KEY=your_api_key_here

Project Structure

  • src/usdc_arc_mcp_demo/ – Main package code
  • test/ – Tests

Linting

This project uses ruff for linting and code style checks.

To lint your code, run:

hatch run ruff check src/

Or:

hatch shell
ruff check src/

Resources