Web2MD

io.github.kanavsingla28由 GitHub 帳號 kanavsingla28 發布v0.1.0更新於 Oct 27, 2026

Turn any web page into clean Markdown, text or token-bounded RAG chunks (via RapidAPI).

發布方自己的服務：Web2md

已驗證STDIO僅桌面網頁搜尋與抓取知識與記憶

概覽

AI 產生的概覽

Web2MD 透過 RapidAPI 的 Web2MD 服務抓取網頁，回傳乾淨的 Markdown、純文字、中繼資料或依 token 切分的 RAG 分塊。

可以做什麼
  • 抓取網頁並以 Markdown、文字或 JSON 回傳正文，可選擇包含連結、圖片與表格
  • 把網頁依標題層級切成以 token 計量的分塊，可設定重疊，供 RAG 與向量化使用
  • 把手上既有的原始 HTML 轉換成 Markdown 或純文字
  • 讀取網頁的標題、作者、發佈日期、描述、站台名稱、語言與閱讀時間
適用情境
適合需要讓助理直接取得可讀的網頁內容或可直接用於 RAG 的分塊、又不想自行建置抽取流程的情境，且可接受使用附免費額度的第三方抽取服務。
執行需求
以本機程序透過 npx 執行（npm 套件 web2md-rag-mcp），需要 Node.js 22 或更新版本。需要環境變數 RAPIDAPI_KEY，來自 RapidAPI 上 Web2MD 的訂閱；BASIC 方案免費，每月 500 次請求。需要能連線至 RapidAPI 閘道的網路。
安裝前請注意
RAPIDAPI_KEY 金鑰會傳送給 RapidAPI 閘道，所抓取的每個網址都會由該第三方服務處理。免費額度之外另有付費方案，配額或速率限制可能用盡。抓取在伺服器端進行，內網與私有位址會被阻擋，並遵守 robots.txt。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Web2MD，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

Web2MD MCP server

An MCP server that turns any web page into clean Markdown, plain text or token-bounded RAG chunks, using the Web2MD API on RapidAPI.

[npm] [CI]

What it does

  • read_url: fetch a web page and return its main content as Markdown or plain text, without nav, ads or boilerplate.
  • chunk_url: fetch a web page and split it into heading-aware chunks sized in tokens, for RAG and embeddings.
  • convert_html: convert raw HTML you already have into Markdown or plain text.
  • page_metadata: get a page's title, author, published date, description and similar fields without the full content.

Setup in 3 steps

  1. Subscribe to Web2MD on RapidAPI. The BASIC plan is free and includes 500 requests per month.
  2. Copy your X-RapidAPI-Key from the Endpoints tab of the listing.
  3. Add the server to your client.

Requires Node.js 22 or newer.

Claude Code:

bash
claude mcp add web2md -e RAPIDAPI_KEY=your-key -- npx -y web2md-rag-mcp

Claude Desktop (claude_desktop_config.json) and Cursor (~/.cursor/mcp.json) use the same JSON:

json
{  "mcpServers": {    "web2md": {      "command": "npx",      "args": ["-y", "web2md-rag-mcp"],      "env": { "RAPIDAPI_KEY": "your-key" }    }  }}

Windsurf: put the same block in ~/.codeium/windsurf/mcp_config.json.

Tools

ToolWhat it doesArgumentsReturns
read_urlFetch a page as clean Markdown or texturl (up to 2048 chars); format: markdown, text or json; include_links, include_images, include_tablesTitle, token count and the content; format: "json" returns the full JSON document
chunk_urlSplit a page into RAG chunksurl; max_tokens 64-8192 (default 512); overlap_tokens 0-1024 (default 50); include_links, include_images, include_tablesJSON with total_tokens and chunks, each with its heading path and token count
convert_htmlConvert raw HTMLhtml (up to 5,000,000 chars); optional url to resolve relative links; format; include_links, include_images, include_tablesSame as read_url
page_metadataGet page metadataurlJSON with title, author, date, description, site name, language, canonical URL, image, word count, reading time

Limits and plans

PlanPriceRequests per month
BASIC$0500
PRO$910,000
ULTRA$2960,000
MEGA$79250,000
  • RapidAPI rate limit: 1,000 requests per hour.
  • Pages up to 5 MB.
  • robots.txt is respected.
  • JavaScript-heavy pages may return no_content. Rendering support is planned.

Errors

Tool errors look like Web2MD error [code]: message. Input-validation failures (a bad URL, out-of-range numbers) come from the MCP SDK as MCP error -32602: Input validation error ... instead.

CodeMeaning
missing_keyRAPIDAPI_KEY is not set
invalid_keyRAPIDAPI_KEY contains characters not allowed in an HTTP header, often a pasted newline
rapidapi_authRapidAPI rejected the key, or you are not subscribed
rapidapi_quotaYour plan's quota or rate limit is used up
invalid_requestThe request failed validation (HTTP 422)
invalid_url400: not http/https, has credentials, no host, bad port, or longer than 2048 chars
blocked_destination400: host resolves to a private, loopback, link-local or metadata address; port not 80/443; localhost/.local/.internal. Applies to every redirect
dns_error400: the host does not resolve
robots_disallowed403: the site's robots.txt disallows the web2md user agent for that path
page_too_large413: page larger than 5 MB
unsupported_content_type415: not HTML
no_content422: fewer than 10 words of main content, often a JavaScript-only page
host_rate_limited429: per-target-site limit that protects the sites fetched. It is not your quota
target_blocked502: the site answered 401/403/429/503, often a bot wall
target_error502: the site answered another 4xx/5xx
fetch_failed502: could not connect, or TLS failed
too_many_redirects502: more than 5 redirects
fetch_timeout504: the fetch took more than 15 s
timeoutThe Web2MD request timed out
network_errorThe request could not reach the API
bad_responseThe API returned a non-JSON success response
http_<status>Any other HTTP failure, with a short snippet of the response
internal_errorAn unexpected error inside the MCP server

Privacy

Your key is sent only to the RapidAPI gateway (web2md-webpage-to-markdown-rag-chunks.p.rapidapi.com) and is never logged.

Development

bash
npm cinpm testnpm run lintnpm run buildRAPIDAPI_KEY=your-key npm run smoke

Licence

MIT

來源：README.md，提交 ff8332c

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

1
  1. v0.1.0最新Oct 17, 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

其他 Web2md 整合

Web2md

org.web2md官方發布者

MCP Server for Web2MD — convert URLs to Markdown from Claude Desktop, Cursor, etc.

Streamable HTTP可網頁執行驗證方式
網頁搜尋與抓取需要憑證Nov 3, 2026

Web2md

由 GitHub 帳號 astra-intelligence 發布

Web2md 將公開網頁轉換成乾淨、適合大型語言模型使用的 Markdown，讓助理直接讀取並重用頁面內容。

Streamable HTTP可網頁執行
網頁搜尋與抓取2 個工具Oct 29, 2026

Web2MD MCP Server

由 GitHub 帳號 astra-intelligence 發布

將公開網頁 URL 轉換為乾淨、可讀的 Markdown，供 AI 助理使用，並去除廣告、導覽和樣板內容。

STDIO僅桌面
網頁搜尋與抓取尚未驗證Oct 24, 2026