Sponsored by Deepsite.site

USASpending MCP

Created By
1102tools11 days ago
MCP server for USASpending.gov: federal contract and award data across all agencies, FFATA subawards, recipient profiles, agency depth (sub-agencies, federal accounts, object classes), award detail rollups, transaction-level and geographic search, IDV depth, and Treasury federal accounts. 55 tools.
Overview

USASpending MCP

A Model Context Protocol server that wraps the USASpending.gov REST APIs as deterministic tool calls. Built for federal contracting officers, GS-1102 contract specialists, contract analysts, market research teams, and small business government contractors who need plain-English access to federal spending and award data.

55 tools, the deepest USASpending coverage of any public MCP. Hardened across multiple live audit rounds against production endpoints, plus Hypothesis-driven property tests. MIT licensed. No API key required.

What it does

Award Search

  • Search awards across all federal agencies by NAICS, PSC, set-aside type, fiscal year, vendor, recipient, agency
  • Geographic filters: place of performance state, county, congressional district, country, recipient location
  • Time-window filters: action date, award date, period of performance start/end
  • Returns ceiling, obligated, contract type, set-aside, NAICS, PSC, agency hierarchy

Award Detail and Lookups

  • Lookup by PIID (contracts), FAIN (assistance awards), URI, or generated unique award ID
  • Award detail rollups across base + options + modifications
  • Award funding by federal account, object class, program activity, fiscal year
  • Transaction-level history showing every obligation event over the life of the award
  • Sub-award rollups linked to prime award

FFATA Subawards

  • Subaward search across all FFATA reporting recipients
  • Acquisition subcontracts and assistance grant subawards
  • Subaward detail with prime award linkage

Recipient Profiles

  • Lookup by name, recipient unique ID, or DUNS legacy
  • Recipient hierarchy (parent, child, branch, division)
  • Recipient award history broken down by agency, NAICS, PSC, fiscal year

Agency Depth

  • Toptier agency overview (overall budget, obligations, top recipients, top NAICS)
  • Sub-agency listings under any toptier agency
  • Federal accounts owned by an agency
  • Object class and program activity breakdowns
  • Agency awards filtered by any tier of the hierarchy

Spending Analytics

  • Spending by category: recipient, agency, sub-agency, federal account, program activity, object class, NAICS, PSC, state, county, district, country
  • Spending over time: monthly, quarterly, fiscal year buckets
  • Aggregate counts and totals across any filter combination

Geographic Search

  • State profiles with award totals and top recipients
  • Filter awards by place of performance or recipient location
  • Cross-state spending comparisons

IDV (Indefinite Delivery Vehicle) Depth

  • IDV child orders and ceiling burn
  • Track task orders against ceiling
  • Vehicle utilization by year and agency

Code Lookups

  • NAICS autocomplete, full-text search, hierarchy, and detail
  • PSC autocomplete, filter tree, free-text search
  • Agency toptier and subtier listings

Federal Accounts

  • Treasury federal account lookups
  • Federal account spending breakdowns by object class and program activity

Use cases

  • Pre-award market research (FAR Part 10): see who's been winning what at which agencies
  • Vendor due diligence: pull a vendor's full federal award history before negotiation or teaming
  • Competitive intelligence: identify primes holding IDIQ vehicles in your NAICS for teaming
  • Set-aside research: 8(a), SDVOSB, WOSB, HubZone award patterns
  • Spending oversight: agency rollups for OIG/GAO reviews
  • Small business: find opportunities to sub on existing IDIQs

Compatibility

  • Claude Desktop (one-click .mcpb install or Copy JSON)
  • Codex (ChatGPT) via TOML config or codex mcp add
  • Gemini CLI via ~/.gemini/settings.json
  • Copilot via .vscode/mcp.json in VS Code
  • Claude Code, Cursor, Cline, Zed, Continue, and any other MCP-compatible client

Install

No API key required.

{
  "mcpServers": {
    "usaspending-gov": {
      "command": "uvx",
      "args": ["--refresh-package", "usaspending-gov-mcp", "--from", "usaspending-gov-mcp", "usaspending-mcp"]
    }
  }
}

TOML config (Codex):

[mcp_servers.usaspending]
command = "uvx"
args = ["--refresh-package", "usaspending-gov-mcp", "--from", "usaspending-gov-mcp", "usaspending-mcp"]

PyPI: pip install usaspending-gov-mcp or uvx --from usaspending-gov-mcp usaspending-mcp

Example prompts

  • "Show me the top 10 AFRL contracts awarded in FY2025 by dollar value, with vendor, amount, and description."
  • "Pull the 12-month award history for Leidos. Break down by agency, NAICS, and ceiling vs obligated amounts."
  • "Who is winning 8(a) awards at DHS in the last fiscal year, and for how much?"
  • "Show me all SDVOSB awards across the federal government in FY25 under NAICS 541512."
  • "Pull all subawards from prime PIID HQ003424F0042. Who got what and for how much?"
  • "Find IDIQ vehicles at DoD under NAICS 541512 awarded in the last 24 months so I can see which primes I could team on."
  • "Break down NAVSEA spending in FY25 by NAICS and recipient."
  • "Compare CECOM and AFRL spending under PSC R408 over the last three fiscal years."
  • "Pull the full transaction history for award PIID W912DY24F0123, including every modification and obligation event."

Hardening

Independently hardened across multiple live audit rounds against production USASpending endpoints, plus Hypothesis-driven property tests. Each release ships a testing.md documenting bugs found and fixed during hardening. Pydantic models use extra="forbid" to surface API drift instead of silently dropping fields. Defensive response parsing guards against partial outages, schema changes, and pagination edge cases.

Source

Server Config

{
  "mcpServers": {
    "usaspending-gov": {
      "command": "uvx",
      "args": [
        "--refresh-package",
        "usaspending-gov-mcp",
        "--from",
        "usaspending-gov-mcp",
        "usaspending-mcp"
      ]
    }
  }
}
Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
Tavily Mcp
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.
CursorThe AI Code Editor
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
Playwright McpPlaywright MCP server
Amap Maps高德地图官方 MCP Server
RedisA Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
DeepChatYour AI Partner on Desktop
WindsurfThe new purpose-built IDE to harness magic
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
Serper MCP ServerA Serper MCP Server
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
ChatWiseThe second fastest AI chatbot™