About mcp-url2markdown
mcp-url2markdown converts web pages at supplied URLs into clean, formatted Markdown using crawl4ai. It is an MCP server for clients such as Cursor, cline, and roo code.
Key features
- 01URL-to-Markdown conversion
- 02Clean, formatted page output
- 03Uses crawl4ai
Use cases
- 01Convert a documentation page to Markdown
- 02Retrieve web content in a structured format
MCP support
Exposes URL-to-Markdown conversion to MCP clients. The README shows configuration examples for Cursor, cline, and roo code.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmcp-url2markdown
基于 crawl4ai 根据提供的url把网页内容转为干净，格式化的markdown内容
快速开始
使用uv安装
git clone https://github.com/sungithubid/mcp-url2markdown.git
uv sync
使用
1. FastMCP cli run server
source .venv/bin/activate
fastmcp dev server.py
打开http://127.0.0.1:6274/ 测试
2. 使用Cursor，cline，roo code等工具
配置
{
"mcpServers": {
"url2md": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-url2markdown",
"run",
"server.py"
],
"env": {},
"disabled": false,
"autoApprove": [],
"alwaysAllow": []
}
}
}
使用roo code测试 输入
把如下网址的网页内容转成markdown输出
https://api-docs.deepseek.com/zh-cn/guides/kv_cache
执行与输出
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.