美國聯邦標案 / 補助 / 貸款搜尋

us_search_awards

台灣專屬MIT

**關鍵字 / Keywords**: 美國政府採購聯邦支出標案承包商補助 subaward NAICS federal spending contract grant loan recipient vendor procurement USASpending FY DOD DOE NASA GSA agency Lockheed Boeing SpaceX prime awardee

Scope: US federal awards on USASpending.gov (contracts / grants /
loans / direct payments / IDVs / other) — the machine-readable
counterpart of TW 政府電子採購網 (`pcc-tender`).

Full-text + filter search over `spending_by_award`. Every result row
surfaces `generated_internal_id` (feed to `us_get_award_details`)
plus a deep link back to usaspending.gov.

Endpoint:
    POST https://api.usaspending.gov/api/v2/search/spending_by_award/

Args:
    keyword: free-text over award description (upstream `keywords[]`).
    recipient: recipient-name substring (e.g. "Lockheed Martin",
               "Booz Allen"). Case-insensitive.
    awarding_agency: awarding-agency name substring (toptier tier,
                     e.g. "Department of Defense").
    naics_codes: filter by NAICS industry codes (e.g. `["336411"]`
                 Aircraft Manufacturing; `["541511"]` Custom Computer
                 Programming).
    psc_codes: filter by PSC (Product / Service Code).
    award_group: convenience bucket — `contracts` (default) · `grants`
                 · `loans` · `direct_payments` · `other` · `idvs`.
                 Overridden by `award_type_codes`.
    award_type_codes: explicit letter/number codes
                      (e.g. `["A","B","C","D"]` for contracts).
    date_from / date_to: YYYY-MM-DD `action_date` window (default
                         = current federal FY25 · 2024-10-01 →
                         2025-09-30). Earliest supported by the
                         endpoint is 2007-10-01.
    amount_min / amount_max: obligation-amount bounds in USD.
    place_of_performance_state: 2-letter US state code (e.g. "TX").
    page: 1-based page number.
    limit: rows per page (max 100).
    sort: `"Award Amount"` (default) · `"Award ID"` · `"Recipient
          Name"` · `"Start Date"` · `"End Date"` · `"Description"` ·
          `"Awarding Agency"` · `"Awarding Sub Agency"`.
    order: `"asc"` | `"desc"`.

Returns dict with `results` (row list · each has Award ID,
Recipient Name, Award Amount, Awarding Agency, `generated_internal_id`,
`original_url` deep link), `page_metadata` (page / total /
has_next), and `filters_applied` echo. License:
"Creative Commons Zero v1.0 Universal (CC0-1.0)".
Rate-limited to ~5 req/sec.

輸入 schema

{
  "properties": {
    "keyword": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Keyword"
    },
    "recipient": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Recipient"
    },
    "awarding_agency": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Awarding Agency"
    },
    "naics_codes": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Naics Codes"
    },
    "psc_codes": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Psc Codes"
    },
    "award_group": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": "contracts",
      "title": "Award Group"
    },
    "award_type_codes": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Award Type Codes"
    },
    "date_from": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Date From"
    },
    "date_to": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Date To"
    },
    "amount_min": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Amount Min"
    },
    "amount_max": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Amount Max"
    },
    "place_of_performance_state": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Place Of Performance State"
    },
    "page": {
      "default": 1,
      "title": "Page",
      "type": "integer"
    },
    "limit": {
      "default": 20,
      "title": "Limit",
      "type": "integer"
    },
    "sort": {
      "default": "Award Amount",
      "title": "Sort",
      "type": "string"
    },
    "order": {
      "default": "desc",
      "title": "Order",
      "type": "string"
    }
  },
  "title": "us_search_awardsArguments",
  "type": "object"
}

呼叫方式

配置好 Twinkle Hub 的 MCP client 後，agent 會看到 us_search_awards。直接讓它呼叫即可，例如：

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

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

尚未設定 Client？

Claude Desktop 約 3 分鐘即可完成設定 — 下載 .mcpb 檔案並雙擊即可，或參閱文件中的各 Client 安裝步驟。

查看使用者設定文件

輸入 schema

呼叫​方式

呼叫方式