USA Spending MCP Server

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

A simple MCP server for interacting with the USAspending.gov API.

Requirements

• Python 3.13+
• Poetry OR uv

Installation Options

Option 1: Install via uv (Recommended for quick setup)

uv tool install git+https://github.com/GSA-TTS/arc-usa-spending-mcp-server

Option 2: Development Setup with Poetry

1. Install dependencies:

   poetry install

2. Activate the virtual environment:

   poetry env activate

Simple way to connect to Claude

For uv installation:

1. Get the installed tool path:

   which usa-spending-mcp-server

2. Copy the path into Claude MCP config:

   {
     "mcpServers": {
       "usa-spending": {
         "command": "/path/to/usa-spending-mcp-server",
         "args": [],
         "env": {}
       }
     }
   }

For Poetry development setup:

1. Get path:

   ➜  usa-spending-mcp-server git:(feature/award_spending) poetry run which usa-spending-mcp-server
   /Users/samuellevy/Library/Caches/pypoetry/virtualenvs/usa-spending-mcp-server-4uFFGwlz-py3.13/bin/usa-spending-mcp-server

2. Copy path into Claude MCP config:

   {
     "mcpServers": {
       "usa-spending": {
         "command": "/Users/samuellevy/Library/Caches/pypoetry/virtualenvs/usa-spending-mcp-server-4uFFGwlz-py3.13/bin/usa-spending-mcp-server",
         "args": [],
         "env": {}
       }
     }
   }

3. Anytime you need to update mcp server rerun:

   poetry install

Running the Server

With uv:

usa-spending-mcp-server

With Poetry:

poetry run usa-spending-mcp-server

Code Formatting

This project uses black and isort for code formatting and import sorting.

• Format code with black:

  poetry run black .

• Sort imports with isort:

  poetry run isort .

Project Structure

src/
  usa_spending_mcp_server/
tests/
pyproject.toml
README.md