Download PDFMarkdown Version

Connect Federal Contracts Icp to ChatGPT, Claude and Gemini

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. Turn government spending data into outbound sales triggers.

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.

How Vinkius works: one connection, every tool, in any AI
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.

Complete set · 6 capabilities

The complete USAspending — US federal spending capability set.

These are the exact actions your AI can choose when you ask it to work with USAspending — US federal spending.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through USAspending — US federal spending.

  1. 01

    Company federal footprint

    This capability provides a deep dive into a specific company's federal history. It returns total dollars, agencies served, and their NAICS mix to prove they are a valid ICP.

  2. 02

    Award detail

    This capability pulls a full data card for a specific award ID. It provides the recipient, amount, period, and description text needed for highly personalized outreach.

  3. 03

    Federal icp targets

    This capability aggregates data for all companies receiving federal contract dollars. It helps you discover new targets by listing total awarded, award counts, and agency involvement.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through USAspending — US federal spending.

  1. 04

    New budget triggers

    This capability identifies federal awards where performance has just started. It acts as a pure timing signal for companies that just received new budget to spend.

  2. 05

    Recent contract wins

    This capability retrieves the most recently modified federal contract awards. Use it to find fresh timing signals for outreach based on recipient, NAICS code, or agency.

  3. 06

    Top federal vendors

    This capability ranks the largest federal vendors by dollars awarded. Use it to benchmark your vertical or identify major competitors within a specific agency or NAICS code.

One connector, every AI

USAspending — US federal spending 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 — US federal spending 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

1150ms average. Fast in production.

USAspending — US federal spending is checked daily against the live service.

Daily averagePeak 1153ms
Sep 25Today
Fastest day
1146ms
Slowest day
1153ms
14-day trend
Stable-1%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 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 — US federal spending, so you can see the experience inside your AI.

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

USAspending — US federal spending Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_slWRQdjKKlm0fcs5lUzkqBD40MkwxAgbZK3fzW90/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 — US federal spending capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "federal-contracts-icp-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_slWRQdjKKlm0fcs5lUzkqBD40MkwxAgbZK3fzW90/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? How to give Claude access to USAspending — US federal spending

See all the AI clients this connector works with ↑

Who it's for

Built for the work USAspending — US federal spending owners hand off.

This MCP is built for sales professionals targeting the government-adjacent market.

  • 01

    Outbound Sales Reps

    They use the MCP to find fresh award triggers for personalized outreach.

  • 02

    Enterprise Account Executives

    They use it to verify the federal footprint and budget of large target accounts.

  • 03

    Market Intelligence Analysts

    They use the benchmarking capabilities to map out competitors in specific NAICS codes.

FAQ

Questions USAspending — US federal spending owners ask.

  • 01

    Do I need an API key to use this MCP?

    No. This MCP uses the public federal spending database through an open API that requires no keys or accounts.

  • 02

    Which AI clients can use this MCP?

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

  • 03

    How fresh is the contract data?

    The MCP can access recently modified awards and new budget triggers to provide the most current information available in the public database.

  • 04

    Can I find specific details about a single contract?

    Yes. If you have an award ID, you can use the award detail capability to get the recipient, amount, agency, and description.

  • 05

    How do I know if a company is a good target?

    You can use the company federal footprint capability to see their total dollars, agencies served, and NAICS mix to confirm they meet your ICP criteria.

  • 06

    Do I need an API key or an account?

    No. The federal government publishes its own contract spending data through an open API with no credentials. the same data behind the national contract-expenditure site. There is nothing to issue, rotate or store.

  • 07

    What counts as a "new budget" trigger?

    An award whose performance period just started and that was modified inside your freshness window (default 30 days). The recipient took new money: new scope, new teams, new tooling decisions. Filter by minimum amount to keep only deals big enough to matter, and by NAICS or agency to focus a vertical.

  • 08

    Why do rankings and totals sometimes look partial?

    The open API exposes a ranked, paged view rather than a server-side census per company, so every aggregation works over the most recently modified matching awards in the slice you asked for. The result says how many awards it scanned, and a longer window or deeper paging gives a fuller picture. That is documented in each result, never silently assumed.

  • 09

    How is the public source protected from repeated scans?

    Each distinct query is cached in memory for one hour, so re-asking the same question minutes apart costs nothing upstream. If the source rate-limits, the error tells you to vary the query or try again later instead of hammering in a loop.

Explore

More in Government Public Data

Suggestions

Connect USAspending — US federal spending to Claude, Cursor, ChatGPT & more