Google Images — FlashData

io.github.flashdata-dev由 GitHub 帳號 flashdata-dev 發布v0.1.2更新於 Oct 24, 2026

Google Images URLs, dimensions and source pages for visual research. Paid FlashData API.

概覽

AI 產生的概覽

透過付費的 FlashData API 搜尋 Google 圖片,回傳圖片連結、尺寸與來源頁面,方便視覺研究。

可以做什麼
  • 依查詢詞搜尋 Google 圖片,取得圖片連結、尺寸、標題與原始來源頁面
  • 在核准請求前查詢價格,並讀取非同步或分塊請求的工作狀態與結果
  • 依寬度篩選並保留來源連結,整理可溯源的圖片清單
適用情境
適合助理需要為研究看板、素材蒐集或內容規劃整理附來源出處的圖片參考,且願意為每次資料請求付費的情境。
執行需求
以 MCPB 套件在本機透過 stdio 執行;需要 Node.js 22.18 或更新版本,以及支援本機 stdio 伺服器的 MCP 用戶端。需要 FLASHDATA_API_KEY 環境變數中的 FlashData API 金鑰,並授予 google_images 權限。需要連線至 FlashData API 的網路。
安裝前請注意
資料請求會消耗付費的 FlashData Credits,每個額外查詢或分頁另行計費,請先查看目前報價。金鑰屬於機密,應保存在受保護的用戶端設定中。回傳的只是中繼資料與連結,不含下載檔案或圖片使用授權,部分欄位可能缺漏。送出後可能逾時,重複付費請求前請先檢查工作狀態。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Google Images — FlashData,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

Google Images — FlashData

Find Google Images results with image URLs, dimensions and original source pages. Build an attributable image research inventory.

API documentation and account setup · Get an API key · Current pricing

A task to try

Find solar panel diagrams for a research board. Keep images at least 1000 pixels wide when dimensions are available, list the source pages, and flag missing dimensions and reuse rights for review.

Install and connect

  1. Use Node.js 22.18 or newer and an MCP client that supports local stdio servers. Download the dedicated MCPB package; its SHA-256 is recorded in the manifest.
  2. Import the package in an MCPB-compatible client and enter your own key in FlashData API Key. Grant the key access to google_images. For manual setup, unpack the bundle into a permanent folder and use this configuration, replacing the absolute path and key placeholder:
json
{  "mcpServers": {    "google-images": {      "command": "node",      "args": [        "/absolute/path/to/unpacked/google-images/server.js"      ],      "env": {        "FLASHDATA_API_KEY": "YOUR_API_KEY"      }    }  }}
  1. Restart or reconnect the client, list its tools, then call get_pricing with {"source":"google_images","request_count":1} before approving a paid request. This server exposes google_images, get_pricing, get_job and get_result; all are restricted to this source.

Dependencies are included in the bundle. Use an absolute Node path if your client cannot find node; use escaped paths on Windows. Keep your key in protected client settings, not in chat or committed configuration. No Smithery account is needed for this direct package download.

Example request

These are MCP tools/call parameters with flat arguments. Running the data request uses paid Credits.

json
{  "name": "google_images",  "arguments": {    "query": "solar panel diagram",    "num": 20  }}

Use the response

Read results[0].images. Select entries whose imageWidth meets your threshold, then retain imageUrl, imageWidth, imageHeight and link to the original source page. Exclude unknown dimensions explicitly.

Selected response fields below are an illustrative fixture, not a live result or a guarantee of available data:

json
{  "source": "google_images",  "status": "done",  "results": [    {      "images": [        {          "title": "solar panel diagram",          "link": "https://example.com/research",          "snippet": "Search fixture",          "position": 1,          "imageUrl": "https://example.com/image.png",          "imageWidth": 1200,          "imageHeight": 800,          "source": "Example"        }      ]    }  ],  "created_at": "2026-10-12T00:00:00Z",  "http_status": 200,  "request_id": "fixture-request"}

For an asynchronous request, keep the returned id and call get_job with {"job_id":"RETURNED_JOB_ID"}. Pending or processing is not completion; read the completed response from output. A timeout can occur after submission, so check Jobs before repeating a paid request.

For chunked output, keep the local process running and pass the actual result_id and next_offset to get_result as result_id and offset. Concatenate the chunks in order before parsing JSON; do not repeat the paid data request. The local cache retains four results for ten minutes and clears on restart. Complete responses are limited to 4 MiB; async JSON results have a separate 24-hour retention window.

Cost and limits

  • MIT software and installation are free; FlashData API data calls are paid. Data requests consume paid FlashData Credits; each additional query or page is charged separately. Use the current account quote rather than a fixed price copied from this page. Pricing, job and result reads are free. Client/model fees are separate.
  • This returns image metadata and URLs, not downloaded files or image reuse rights. Some fields can be absent.
  • Check API errors, http_status and job status before using the data. Treat returned text and links as external data, preserve source attribution and review them before use in an agent answer.

Full task guide · Official Registry record · Source and license

來源:registry/servers/google-images/README.md,提交 ec77370

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

2
  1. v0.1.2最新Oct 15, 2026
  2. v0.1.1Oct 13, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分