Twinkle HubTwinkle Hub
Sign in

📌 2026-08-17 added: ⚖️ Taiwan statute time machine — historical article text · revision history · full-text search · citation graph (935 datasets · 35,454+ rows)

View full changelog →

US federal award recipients search

us_search_recipients

TW-specificMIT

**關鍵字 / Keywords**: 美國政府 受款方 承包商 廠商 vendor recipient contractor parent child subsidiary UEI DUNS 公司 非營利 nonprofit university state foreign USASpending federal awardee Lockheed Boeing SpaceX Palantir

Scope: entities (companies / nonprofits / universities / states /
foreign) that received federal awards, rolled up to the parent /
child recipient level.

Endpoint:
    POST https://api.usaspending.gov/api/v2/recipient/

Args:
    keyword: recipient-name substring (case-insensitive).
    award_group: filter by award category — `"all"` (default) ·
                 `"contracts"` · `"grants"` · `"loans"` ·
                 `"direct_payments"` · `"other_financial_assistance"`.
    page: 1-based page number.
    limit: rows per page (max 100).
    sort: `"amount"` (default) · `"name"` · `"duns"` · `"uei"`.
    order: `"asc"` | `"desc"`.

Returns dict with `results` — each row `{id, duns, uei, name,
recipient_level, amount, profile_url}`. `id` suffix tags recipient
level: `-P` parent · `-C` child · `-R` orphan. License:
"Creative Commons Zero v1.0 Universal (CC0-1.0)". Rate-limited
to ~5 req/sec.

Input schema

{
  "properties": {
    "keyword": {
      "title": "Keyword",
      "type": "string"
    },
    "award_group": {
      "default": "all",
      "title": "Award Group",
      "type": "string"
    },
    "page": {
      "default": 1,
      "title": "Page",
      "type": "integer"
    },
    "limit": {
      "default": 20,
      "title": "Limit",
      "type": "integer"
    },
    "sort": {
      "default": "amount",
      "title": "Sort",
      "type": "string"
    },
    "order": {
      "default": "desc",
      "title": "Order",
      "type": "string"
    }
  },
  "required": [
    "keyword"
  ],
  "title": "us_search_recipientsArguments",
  "type": "object"
}

How to call

Once your Twinkle Hub MCP client is configured, your agent will see us_search_recipients. Just ask it to call — example:

# Ask Claude / any MCP client:
請用 us_search_recipients 處理 "…"。

# It will call:
us_search_recipients(input="…")

Haven't set up a client yet?

Claude Desktop in 3 minutes — download the .mcpb and double-click, or see docs for other clients.

See user docs