TidyTools: lead enrichment, RAG Markdown, transcripts, AI crawler checks

io.github.tidytoolsv1.0.0更新於 Oct 1, 2026

Enrich Google Maps leads, crawl docs to RAG Markdown, transcribe podcasts, check AI crawler access.

已驗證Streamable HTTP可網頁執行Media & DesignWeb Search & ScrapingData & Analytics

概覽

AI 產生的概覽

讓助理呼叫五個按用量計費的 Apify 網頁資料工具：潛在客戶聯絡方式擷取、文件轉 Markdown 爬取、文件轉換、音訊影片轉錄，以及 AI 爬蟲存取檢查。

功能
把 MCP 用戶端連接到 Apify 託管的 MCP 伺服器，並限定為五個 TidyTools Actor：Website Contact Extractor（從網站擷取電子郵件與社群帳號）、Website to Markdown Crawler（把頁面轉成 Markdown 供上下文使用）、PDF/Word/Excel 轉 Markdown、Audio & Video Transcriber，以及 AI Crawler Access Checker。它也提供 Apify 的標準輔助工具，例如 get-actor-run、get-dataset-items、get-key-value-store-record 和 abort-actor-run，方便取得較長任務的執行結果。
適用情境
當助理需要網頁來源的資料而不想自行打造爬蟲時使用：補充潛在客戶名單、把文件載入為 Markdown 上下文、轉換文件、轉錄音訊影片，或檢查網站是否封鎖 AI 爬蟲。
執行需求
遠端 MCP 端點 mcp.apify.com，無需安裝。需要免費的 Apify 帳號，執行費用按結果計費。驗證方式為 OAuth 登入，或使用 Authorization 標頭攜帶 Bearer Apify API 權杖。
安裝前請注意
執行費用按結果計入 Apify 帳號，成本隨用量增加（例如每 1,000 個網站、頁面或文件，或每音訊分鐘計費）。Authorization 標頭攜帶 Apify API 權杖，屬於機密，不應出現在共用設定中。工具會抓取第三方網頁，並把網站與文件內容傳送給 Apify 處理。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 TidyTools: lead enrichment, RAG Markdown, transcripts, AI crawler checks，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。

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。

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "tidytools-apify-tools": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=tidytools/website-contact-extractor,tidytools/website-markdown-crawler,tidytools/document-to-markdown,tidytools/audio-transcriber,tidytools/ai-crawler-access-checker"
    }
  }
}

README

TidyTools for AI agents (remote MCP)

Five pay-per-use web data tools that any MCP client (Claude, Cursor, VS Code, n8n AI Agent, ...) can call through Apify's hosted MCP server. Nothing to install: add one URL.

https://mcp.apify.com/?tools=tidytools/website-contact-extractor,tidytools/website-markdown-crawler,tidytools/document-to-markdown,tidytools/audio-transcriber,tidytools/ai-crawler-access-checker

Tools

ToolAsk your agent something likePrice (Apify, Sept 2026)
Website Contact Extractor"Find the email and Instagram of these 50 cafés."$2 per 1,000 websites; nothing found = free
Website to Markdown Crawler"Load the FastAPI docs into context as Markdown."$1 per 1,000 pages ($2.50 when a page needs a browser)
PDF, Word & Excel to Markdown"Turn this PDF into Markdown chunks."$2 per 1,000 documents
Audio & Video Transcriber"Transcribe the latest episode of this podcast and summarize it."$0.006 per audio minute
AI Crawler Access Checker"Does nytimes.com block GPTBot or ClaudeBot?"$2 per 1,000 sites

Connect

OAuth (recommended): add the URL above as a remote MCP server; your client opens an Apify sign-in the first time.

API token:

json
{  "mcpServers": {    "tidytools": {      "url": "https://mcp.apify.com/?tools=tidytools/website-contact-extractor,tidytools/website-markdown-crawler,tidytools/document-to-markdown,tidytools/audio-transcriber,tidytools/ai-crawler-access-checker",      "headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" }    }  }}

You need a free Apify account; runs are billed to it per result (no subscription). Only want one tool? Keep just that one in ?tools=.

Besides the five tools, the server adds Apify's standard helpers (get-actor-run, get-dataset-items, get-key-value-store-record, abort-actor-run) so the agent can fetch results of longer runs.

How it works

The server is Apify's official MCP server (com.apify/apify-mcp-server). The tools parameter limits it to these five Actors, so the agent sees five focused tools instead of thousands. Each Actor's behaviour, limits and output fields are documented on its Apify page.

Listing

Published to the official MCP Registry as io.github.tidytools/tidytools-apify-tools (see server.json). Search: https://registry.modelcontextprotocol.io/v0/servers?search=tidytools

Source of this repo: https://github.com/tidytools/tidytools-apify-mcp

License

MIT (this README and server.json, see LICENSE). The Actors themselves are paid services on Apify.

來源：README.md，提交 6321cc5

工具

0
工具後設資料尚未被收錄。

版本歷史

1
  1. v1.0.0最新Oct 1, 2026