Web Data Toolkit

io.github.leekung125由 GitHub 帳號 leekung125 發布v1.2.0更新於 Oct 24, 2026

YouTube transcripts (video, channel, search), Google Trends, Google Play and App Store reviews.

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取資料與分析

概覽

AI 產生的概覽

遠端 MCP 伺服器,讓助理取得 YouTube 字幕、Google 搜尋熱度,以及 App Store 與 Google Play 的應用程式評論。

可以做什麼
取得單支或多支 YouTube 影片的字幕,附語言、是否為自動產生、字數、標題與頻道。列舉頻道、帳號或播放清單的最新影片並附上字幕,或以搜尋關鍵字直接取得前幾名結果的字幕。查詢最多五個關鍵字的 Google 搜尋熱度:時間趨勢、地區分布與相關查詢。取得 iOS App Store 應用程式的評論與應用程式基本資料。取得 Google Play 應用程式的評論、按讚數與開發者回覆。
適用情境
當你需要快速取得 YouTube 影片或頻道的字幕、比較關鍵字的 Google 搜尋熱度,或彙整 App Store 與 Google Play 的使用者評論時使用。適合市場調查、內容研究與競品評論分析。
執行需求
使用遠端端點,無需安裝或本機執行環境。需在 x-api-key 標頭提供 API 金鑰;可先用共用示範金鑰試用,正式金鑰需提出申請。需能連線至網路,並建議將用戶端逾時設為至少 60 秒。
安裝前請注意
需提供 x-api-key 憑證;示範金鑰為共用且有速率限制與每次呼叫列數上限。每次呼叫都會即時抓取來源資料,較慢的請求可能超過一般逾時。結果過長時會被截斷。僅涵蓋公開資料,字幕可能含自動產生的錯誤,Trends 數值為相對熱度而非搜尋量。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Web Data Toolkit,將其新增到工作區。
  2. 連接 x-api-key 憑證。它們會被私密儲存,絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.leekung125%2Fweb-data-toolkit/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "web-data-toolkit": {
      "type": "http",
      "url": "https://web-data-toolkit.vercel.app/mcp",
      "headers": {
        "x-api-key": "<YOUR_API_KEY>"
      }
    }
  }
}

README

Web Data Toolkit — MCP server

Four public-data tools for any MCP client: YouTube transcripts (one video or a whole channel), Google Trends (interest over time, by region, related queries), and Google Play reviews.

Hosted and remote — there is nothing to install, build, or keep running. Point your client at one URL.

json
{  "mcpServers": {    "web-data-toolkit": {      "type": "http",      "url": "https://web-data-toolkit.vercel.app/mcp",      "headers": { "x-api-key": "YOUR_KEY" }    }  }}

Clients that accept only a URL can carry the key in the query string instead: https://web-data-toolkit.vercel.app/mcp?key=YOUR_KEY

Try it before signing up. Put wdt_demo_public in as the key. It is a shared demo key: rate limited, and capped at 10 rows per call, but every tool answers and you can see the exact shape of the data before you decide anything.

Tools

ToolWhat it returnsRequired
youtube_transcriptTranscript text for up to 50 videos, with language, an auto-generated flag, word count, title and channelurl
youtube_channel_transcriptsEvery recent video of a channel, @handle or playlist, each with metadata and transcript — or pass search: your query to search YouTube and get the top results with transcriptssource
google_trendsInterest over time, interest by region, and top plus rising related queries for up to 5 keywordskeyword
google_play_reviewsRating, text, author, thumbs-up, app version and the developer's replyapp

Question to transcripts in one call. {"source": "search: cold plunge recovery", "max": 3} searches YouTube and returns the top results with full transcripts, so an agent does not have to know which creator to ask first.

Optional arguments are described in each tool's input schema, so your client will show them. Full REST documentation, an OpenAPI specification and an llms.txt live at https://web-data-toolkit.vercel.app.

Getting a key

Start with wdt_demo_public. It is shared, rate limited and capped at 10 rows per call, and every tool answers on it — enough to see the exact shape of the data.

For a personal key with higher limits, open an issue and say roughly what volume you need.

⛔ A RapidAPI subscription (https://rapidapi.com/leetanakung98/api/web-data-toolkit) issues a key for RapidAPI's own gateway. That key authenticates against their endpoint, not this one, so it will not work for MCP. Subscribe there if you want the REST API billed through RapidAPI; come here for MCP.

How it behaves

  • Transport: JSON-RPC 2.0 over Streamable HTTP, protocol 2025-06-18 (it will also negotiate 2025-03-26 and 2024-11-05). The server is stateless: it issues no session id, and GET returns 405 because there is no server-initiated stream.
  • Latency: every call is a live fetch from the source, not a cache. Measured 2026-09-14, one call each: a YouTube transcript in 3.7s, Google Play reviews in 3.8s, a Google Trends keyword in 8.6s, and a whole channel of 25 videos with every transcript in 29.8s; the slowest single call that day was 21s. Set your client timeout to at least 60 seconds.
  • Built for a context window: results come back as a reading, not a dump. One Google Trends keyword is 146 rows and about 37,000 characters of JSON; the MCP answer is around 1,200 characters and says where interest sits against the window, the top regions, and the top and rising related queries. Reviews come back as a star distribution plus one line each; transcripts as title, channel, language and text. Pass raw: true on any tool for every field.
  • Large results: a tool result is truncated at 120,000 characters and says so in its first line, so a whole channel cannot silently blow up a context window. Narrow the request for the rest.
  • Errors: a failed call comes back as an MCP tool result with isError set and the reason in the text, rather than as a protocol error, so an agent can read and recover from it.

Honest limits

  • Public data only. Nothing behind a login, and no personal data beyond the public author name a platform already displays on a review.
  • Transcripts are whatever the platform publishes. Auto-generated captions carry the errors the machine made, and the response tells you which kind you received.
  • Google Trends values are relative interest as Google reports them. They are not search volumes.
  • There is no published uptime figure, because there is not yet enough history to state one honestly.

What's in this repo

This is the whole service, not just a manifest.

api/mcp.js        the MCP protocol handler - tool listing and tool callsapi/rest.js       the plain REST surface, one handler behind vercel.json rewriteslib/tools.js      tool definitions and the upstream calls behind themlib/format.js     row shaping, truncation and the per-call output cappublic/           landing page, openapi.json, llms.txt, robotsvercel.json       the rewrites that map /mcp and /api/* onto the two handlersserver.json       the Model Context Protocol registry manifest

Every credential is read from the environment — see .env.example. The upstream token is used server-side only and never reaches a client. The public demo key is rate-limited and row-capped in lib/format.js so an open endpoint can't run up a bill.

License

MIT — see LICENSE. The license covers this repository; the hosted service is a separate offering with its own terms on RapidAPI.

來源:README.md,提交 6a46739

工具

5

youtube_transcript

Get the full transcript of one or more YouTube videos as clean text.

Returns the transcript text for each video plus its language, whether the captions were auto-generated, word count, title and channel. Comma-separate up to 50 video URLs or ids. Videos with no captions come back with a status instead of text.

輸入參數rawurl必填langsegmentstranslateTo

youtube_channel_transcripts

Search YouTube, or list a channel or playlist, and return every video with its transcript.

Enumerates the newest videos of a channel, @handle or playlist and returns each video's metadata and transcript in a single call. Pass "search: your query" instead of a channel to go straight from a question to transcripts without knowing which creator to ask - the top results come back with full transcripts. Useful for building a corpus on a topic or from one creator.

輸入參數maxrawlangsource必填

app_store_reviews

App Store customer reviews for an iOS app, by country and sort order.

Rating, title, text, author, app version and the review date for any iOS App Store app, plus the app's own metadata row (name, seller, price, average rating, rating count).

輸入參數app必填maxrawsortcountrymaxRatingminRating

google_play_reviews

Google Play reviews for an Android app, by country and language.

Rating, text, author, thumbs-up count, app version and the developer's reply for any Google Play app.

輸入參數app必填maxrawlangratingcountry

版本歷史

2
  1. v1.2.0最新Oct 1, 2026
  2. v1.1.0Sep 16, 2026

評分

已滿足適用檢查項的 100%

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 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分