An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Usaspending Federal Spending to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Audit government spending and track agency awards through your agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 32 capabilities

We ship only the actions that matter.

Capability set01 / 08

01-04

4 capabilities in this set.

Part of 32 available through USAspending.

  1. 01

    Get subawards

    This capability retrieves subawards linked to a specific parent award.

  2. 02

    Autocomplete location

    Use this to find specific locations based on your search text.

  3. 03

    Autocomplete recipient

    This capability finds recipient names and UEI numbers using search text.

  4. 04

    Download search

    Get a ZIP file containing Awards, Subawards, and Transactions for your search.

Capability set02 / 08

05-08

4 capabilities in this set.

Part of 32 available through USAspending.

  1. 05

    Get agency awards

    This capability pulls a summary of transactions and obligations for a specific agency.

  2. 06

    Get agency awards count

    Get the count of award types for agencies within a specific fiscal year.

  3. 07

    Get agency sub agencies

    This capability lists sub-agencies and offices that have obligated amounts.

  4. 08

    Get award

    Retrieve full details regarding a specific federal award.

Capability set03 / 08

09-12

4 capabilities in this set.

Part of 32 available through USAspending.

  1. 09

    Get award types

    This capability provides a map of award types organized by grouping.

  2. 10

    Get data dictionary

    Access the JSON structure of the Rosetta Crosswalk Data Dictionary.

  3. 11

    Get disaster agency spending

    Get insights into which agencies are receiving disaster-related funding.

  4. 12

    Get glossary

    Retrieve a list of glossary terms and their definitions.

Capability set04 / 08

13-16

4 capabilities in this set.

Part of 32 available through USAspending.

  1. 13

    Get recipient children

    This capability pulls recipient details based on a specific identifier.

  2. 14

    Get recipient state

    Get basic information about a specified state.

  3. 15

    Get toptier agencies

    This capability lists all top-tier agencies and their relevant data.

  4. 16

    List recipients

    Get a list of all recipients stored in the database.

Capability set05 / 08

17-20

4 capabilities in this set.

Part of 32 available through USAspending.

  1. 17

    Search new awards over time

    This capability identifies time periods where new awards were issued.

  2. 18

    Search spending by category

    Get grouped spending data for visualizations by agency, recipient, or CFDA.

  3. 19

    Autocomplete awarding agency

    Find awarding agencies that match your search text.

  4. 20

    Autocomplete glossary

    Search for specific glossary terms using text input.

Capability set06 / 08

21-24

4 capabilities in this set.

Part of 32 available through USAspending.

  1. 21

    Bulk download awards

    Generate a ZIP file containing award data in CSV format.

  2. 22

    Get agency budgetary resources

    Retrieve budgetary resources and obligations for an agency by fiscal year.

  3. 23

    Get agency overview

    Get a high-level overview for an agency's details page.

  4. 24

    Get award funding

    Retrieve federal account and agency funding information for a specific award.

Capability set07 / 08

25-28

4 capabilities in this set.

Part of 32 available through USAspending.

  1. 25

    Get disaster award amount

    Get obligation and outlay aggregations for disaster-related awards.

  2. 26

    Get disaster overview

    Access an overview of disaster and emergency spending.

  3. 27

    Get download status

    Check the current progress of a requested download job.

  4. 28

    Get recipient

    Retrieve specific details for an individual recipient.

Capability set08 / 08

29-32

4 capabilities in this set.

Part of 32 available through USAspending.

  1. 29

    Get transactions

    Get all transactions related to a specific parent award.

  2. 30

    Search spending by award

    Search and filter through federal awards.

  3. 31

    Search spending by geography

    Analyze spending by state, county, or congressional district.

  4. 32

    Search spending over time

    Get aggregated transaction amounts over specific time periods.

Real work

What teams actually run

01

Regional Spending Audits

Analyze how much federal money is flowing into a specific county or congressional district.

02

Agency Oversight

Monitor the budget resources and obligations of specific departments like the DOJ or DOE.

03

Contractor Investigation

Track specific recipients and their subaward connections to see where funds are distributed.

04

Disaster Response Tracking

Review agency spending and obligation amounts related to emergency and disaster funding.

Automate a task

Put USAspending to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

USAspending works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put USAspending to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1111ms average. Fast in production.

USAspending is checked daily against the live service.

Daily averagePeak 1304ms
Oct 3Today
Fastest day
860ms
Slowest day
1304ms
14-day trend
Slowing+19%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 32 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of USAspending, so you can see the experience inside your AI.

It does not authenticate your account with USAspending. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

USAspending Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_SGqOxUwCS5vSVfgBiSV43hzg4gnIzYvjeGWqLvnr/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — USAspending capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "usaspending-federal-spending-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_SGqOxUwCS5vSVfgBiSV43hzg4gnIzYvjeGWqLvnr/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up USAspending in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work USAspending owners hand off.

This MCP is built for professionals who need to monitor or report on federal fund allocation.

  • 01

    Policy Researchers

    Gather agency obligation data to build evidence-based reports.

  • 02

    Journalists

    Track federal contracts and grants in specific regions for investigative work.

  • 03

    Data Analysts

    Export and analyze spending trends across government sectors.

FAQ

Questions USAspending owners ask.

  • 01

    Do I need an API key for this MCP?

    You can use the MCP without a key, but providing a USAspending API key allows for higher rate limits when performing heavy queries.

  • 02

    Which clients can I use with this MCP?

    You can use this with any MCP-compatible client, including Claude, Cursor, and Windsurf.

  • 03

    Can I download the data for offline analysis?

    Yes, the MCP includes capabilities to generate ZIP files of awards, subawards, and transactions for bulk downloading.

  • 04

    How current is the data?

    The MCP connects to the official USAspending database, providing access to real-time federal financial data.

  • 05

    Can I filter spending by specific locations?

    Yes, you can request spending breakdowns by state, county, or even specific congressional districts.

  • 06

    How do I get an overview of a specific agency's spending?

    Use the get_agency_overview capability by providing the agency's toptier code. The agent will return high-level data including total obligations and budgetary resources.

  • 07

    Can I see which sub-agencies are spending the most within a department?

    Yes! The get_agency_sub_agencies capability lists all sub-agencies and offices associated with a toptier agency, along with their respective obligated amounts.

  • 08

    Is it possible to filter federal awards by geographic location?

    Absolutely. Use search_spending_by_geography to aggregate spending data by state, county, or district, or use search_spending_by_award with geographic filters.

Explore

More in Industry Titans

Suggestions

Connect USAspending to Claude, Cursor, ChatGPT & more