Web2MD

io.github.kanavsingla28由 GitHub 账号 kanavsingla28 发布v0.1.0更新于 Oct 27, 2026

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

发布方自己的服务：Web2md

已验证STDIO仅桌面网页搜索与抓取知识与记忆

概览

AI 生成的概览

Web2MD 通过 RapidAPI 的 Web2MD 服务抓取网页，返回干净的 Markdown、纯文本、元数据或按 token 切分的 RAG 分块。

可以做什么
  • 抓取网页并以 Markdown、文本或 JSON 返回正文，可选包含链接、图片和表格
  • 把网页按标题层级切成以 token 计量的分块，可设重叠，用于 RAG 与向量化
  • 把已有的原始 HTML 转换为 Markdown 或纯文本
  • 读取网页的标题、作者、发布日期、描述、站点名、语言和阅读时长
适用场景
适合需要让助手直接获得可读网页内容或可直接用于 RAG 的分块、又不想自建抽取流程的场景，且可以接受使用带免费额度的第三方抽取服务。
运行要求
以本地进程方式通过 npx 运行（npm 包 web2md-rag-mcp），需要 Node.js 22 或更高版本。需要环境变量 RAPIDAPI_KEY，来自 RapidAPI 上 Web2MD 的订阅；BASIC 套餐免费，每月 500 次请求。需要能访问 RapidAPI 网关的网络。
安装前请注意
RAPIDAPI_KEY 密钥会发送给 RapidAPI 网关，所抓取的每个网址都会由该第三方服务处理。免费额度之外有付费套餐，配额或速率限制可能被用尽。抓取在服务端进行，内网和私有地址会被拦截，并遵守 robots.txt。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Web2MD，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

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

来源：README.md，提交 ff8332c

工具

0
SourceWeft 尚未在沙箱中启动过该软件包，因此其工具未知。

版本历史

1
  1. v0.1.0最新Oct 17, 2026

评分

已满足适用检查项的 50%

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25 分

    请保持端点能够响应 MCP 握手；SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

其他 Web2md 集成

Web2md

org.web2md官方发布者

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

Streamable HTTP可网页运行鉴权
网页搜索与抓取需要凭据Nov 3, 2026

Web2md

由 GitHub 账号 astra-intelligence 发布

Web2md 把公开网页转换成干净、适合大模型使用的 Markdown，让助手直接读取并复用页面内容。

Streamable HTTP可网页运行
网页搜索与抓取2 个工具Oct 29, 2026

Web2MD MCP Server

由 GitHub 账号 astra-intelligence 发布

将公开网页 URL 转换为干净、可读的 Markdown，供 AI 助手使用，并去除广告、导航和样板内容。

STDIO仅桌面
网页搜索与抓取尚未验证Oct 24, 2026