Converts web pages into clean Markdown format, extracting content while preserving links and structure for documentation reading, content analysis, and information gathering.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Read-Website read the latest documentation on OpenAI's API from their website"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
一个快速、高效的网页内容提取工具，将网页转换为干净的Markdown格式，适用于AI代理、IDE和LLM管道。 A fast and efficient web content extraction tool that converts web pages into clean Markdown format, suitable for AI agents, IDEs, and LLM pipelines.## 工具列表 Tool List
本MCP服务封装下列工具，可让模型通过标准化接口调用以下功能。 本MCP服务封装下列工具，可让模型通过标准化接口调用以下功能。
工具 Tool | 描述 Description |
read_website | Fast, token-efficient web content extraction - ideal for reading documentation, analyzing content, and gathering information from websites. Converts to clean Markdown while preserving links and structure. |
工具在线测试： https://mcp.xiaobenyang.com/inspector/1777316659753987
Online Tool test https://mcp.xiaobenyang.com/inspector/1777316659753987
Related MCP server: Website to Markdown MCP
如何获取 XBY-APIKEY ？ How to get XBY-APIKEY ?
访问小笨羊科技网站 https://xiaobenyang.com，注册用户即可获得APIKEY Visit XiaoBenYang website https://xiaobenyang.com, register and get the APIKEY.
{
"mcpServers": {
"网页内容提取工具": {
"headers": {
"XBY-APIKEY": "<YOUR_XBY_APIKEY>"
},
"type": "sse",
"url": "https://mcp.xiaobenyang.com/1777316659753987/sse"
}
}
}{
"mcpServers": {
"网页内容提取工具": {
"headers": {
"XBY-APIKEY": "<YOUR_XBY_APIKEY>"
},
"type": "streamable_http",
"url": "https://mcp.xiaobenyang.com/1777316659753987/mcp"
}
}
}{
"mcpServers": {
"网页内容提取工具": {
"command": "npx",
"args": [
"-y",
"xiaobenyang-mcp"
],
"env": {
"XBY_APIKEY": "<YOUR_XBY_APIKEY>",
"mcpId": "1777316659753987",
},
"transport": "stdio"
}
}
}
Fast, token-efficient web content extraction - ideal for reading documentation, analyzing content, and gathering information from websites. Converts to clean Markdown while preserving links and structure.
Inputs: url (required), pages, cookiesFile.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined as web content extraction, making it impossible for an agent to misselect between non-existent alternatives.
The single tool name 'read_website' follows a clear verb_noun pattern, and with no other tools present, there is no inconsistency to evaluate. The naming is straightforward and predictable for this minimal set.
One tool is too few for a server named 'Read-Website', as it suggests a narrow scope that might limit functionality. While the tool is well-described, a single tool often feels insufficient for robust web content interactions, such as handling errors, managing sessions, or providing additional utilities like summarization or filtering.
The tool surface is severely incomplete for web content extraction. It lacks essential operations such as handling different content types (e.g., PDFs, images), managing cookies or authentication, retrying failed requests, or providing metadata extraction. This gap will likely cause agent failures in real-world scenarios beyond basic reading.
Convert any webpage to clean LLM-ready markdown, extraction-first, with article and news modes.
Web pages and whole sites to clean Markdown for RAG and AI agents. Crawls links and sitemaps.
Turn any webpage into clean Markdown for LLM/agent pipelines. Free tier; paid 1 USDC = 1000 req.
Turn any web page URL or HTML into clean Markdown or plain text for an LLM to read.