How to Use the USAspending (Federal Spending) MCP in Claude Code

Q: How do I script spending pattern analysis using USAspending (Federal Spending) with Claude Code?

Use searchspendingovertime in a shell script. You can capture the aggregated data and then use standard Linux tools to calculate variances or plot simple text reports from the resulting JSON output.

Q: Can I automate disaster reporting using USAspending (Federal Spending) with Claude Code?

Yes. A script runs getdisasteroverview for a summary and then loops through results, calling getdisasterawardamount for each major agency to compile a comprehensive spending report.

Q: How do I find all related spending by agency using USAspending (Federal Spending) with Claude Code?

Run getagencyawards against a target agency. This provides transaction summaries, and you can then use the resulting award IDs to call searchspendingbyaward, compiling a full financial picture from the command line.

Q: Does USAspending (Federal Spending) support checking recipient details using Claude Code?

Yes. You run listrecipients to get IDs, and then use a simple loop to call getrecipient for each ID. The output is clean text you can pipe into an audit log.

Script USAspending (Federal Spending) workflows with Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect USAspending (Federal Spending) MCP to Claude Code

Create your Vinkius account to connect USAspending (Federal Spending) to Claude Code 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 USAspending (Federal Spending) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run spending analysis scripts with the MCP Server.

Start a CI/CD script by calling `search_spending_by_geography` to filter awards based on location codes. The output is clean data you can pipe directly into a reporting engine or database write command. You also run budget checks using `get_agency_budgetary_resources`. This allows your shell script to check if an agency has sufficient funds before initiating a major spending process, all from the terminal.

Automate USAspending (Federal Spending) award lookups.

Need details on a specific contract? Run `get_award` via a command line script. This returns structured data that you can immediately parse with standard Unix tools like `jq`. You then follow up by running `search_new_awards_over_time` to track trends over months. To verify funding, pipe an award ID into a request for `get_award_funding`, giving your automation step the exact financial context required.

Download and manage USAspending (Federal Spending) data flows.

Set up a cron job that executes `bulk_download_awards` to generate an award ZIP file nightly. The script then checks the download status using `get_download_status` before sending a completion notification. If you only want subaward details, run `get_subawards` against a parent ID and pipe the resulting list directly into another processing utility.

Setup guide

Set up USAspending (Federal Spending) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see usaspending-federal-spending-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest USAspending (Federal Spending) transactions." It will automatically discover and invoke the available USAspending (Federal Spending) tools.

Terminal

claude mcp add --transport http usaspending-federal-spending-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the USAspending (Federal Spending) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "usaspending-federal-spending-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 USAspending. 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 USAspending (Federal Spending) 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 USAspending (Federal Spending) MCP in Claude Code

Use `search_spending_over_time` in a shell script. You can capture the aggregated data and then use standard Linux tools to calculate variances or plot simple text reports from the resulting JSON output.

Yes. A script runs `get_disaster_overview` for a summary and then loops through results, calling `get_disaster_award_amount` for each major agency to compile a comprehensive spending report.

This server touches recipient names and Unique Entity Identifiers (UEI). When using Claude Code, you can write pre-processing steps to filter out or sanitize these specific identifiers before they are passed through your pipeline.

Run `get_agency_awards` against a target agency. This provides transaction summaries, and you can then use the resulting award IDs to call `search_spending_by_award`, compiling a full financial picture from the command line.

Yes. You run `list_recipients` to get IDs, and then use a simple loop to call `get_recipient` for each ID. The output is clean text you can pipe into an audit log.

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

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript