Web Data Toolkit

io.github.leekung125由 GitHub 账号 leekung125 发布v1.2.0更新于 Oct 24, 2026

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

已验证Streamable HTTP可网页运行网页搜索与抓取数据与分析

概览

AI 生成的概览

远程 MCP 服务器,让助手获取 YouTube 字幕、Google 搜索热度,以及 App Store 与 Google Play 的应用评论。

可以做什么
获取单条或多条 YouTube 视频的字幕,附语言、是否为自动生成、字数、标题与频道。列举频道、账号或播放列表的最新视频并附上字幕,或以搜索关键词直接取得前几条结果的字幕。查询最多五个关键词的 Google 搜索热度:时间趋势、地区分布与相关查询。获取 iOS App Store 应用的评论与应用基本信息。获取 Google Play 应用的评论、点赞数与开发者回复。
适用场景
当你需要快速获取 YouTube 视频或频道的字幕、比较关键词的 Google 搜索热度,或汇总 App Store 与 Google Play 的用户评论时使用。适合市场调研、内容研究与竞品评论分析。
运行要求
使用远程端点,无需安装或本地运行环境。需在 x-api-key 请求头提供 API 密钥;可先用共享演示密钥试用,正式密钥需提出申请。需能访问网络,并建议将客户端超时设为至少 60 秒。
安装前请注意
需提供 x-api-key 凭据;演示密钥为共享且有速率限制与每次调用行数上限。每次调用都会实时抓取来源数据,较慢的请求可能超过一般超时。结果过长时会被截断。仅涵盖公开数据,字幕可能含自动生成的错误,Trends 数值为相对热度而非搜索量。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Web Data Toolkit,将其添加到工作区。
  2. 连接 x-api-key 凭据。它们会被私密存储,绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.leekung125%2Fweb-data-toolkit/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "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.

来源: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.

输入参数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.

输入参数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).

输入参数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.

输入参数app必填maxrawlangratingcountry

版本历史

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

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分