Mcp Web Reader
About
让Claude等大语言模型轻松获取和解析任何网页内容，并转化为干净的Markdown。支持双引擎、批量处理，增强AI互联网信息处理能力。
Details
- Author
- zacfire
- Downloads
- 341
- Categories
- Other
Jump to
- Dual engine support: Jina Reader API and local parser
- Automatic fallback from Jina to local parser on failure
- Batch processing of multiple URLs simultaneously
- Force-specific parsing mode with dedicated tools
- Output converted to clean Markdown format
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Mcp Web ReaderCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install from source via git clone and npm install, or globally via npm install -g mcp-web-reader. Configure the server in Claude Desktop’s claude_desktop_config.json (Windows: %APPDATA%, macOS: ~/Library/Application Support/Claude). Then use natural language commands like “Get the content of https://example.com” or “Use Jina Reader to fetch https://example.com”.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp web reader": {
"web-reader": {
"command": "node",
"args": [
"/absolute/path/to/mcp-web-reader/dist/index.js"
]
}
}
}
}McpServers
{
"web-reader": {
"command": "node",
"args": [
"/absolute/path/to/mcp-web-reader/dist/index.js"
]
}
}MCP Web Reader
一个强大的 MCP (Model Context Protocol) 服务器，让 Claude 和其他大语言模型能够读取和解析网页内容。
功能特点
- 🚀 双引擎支持：集成 Jina Reader API 和本地解析器
- 🔄 智能降级：Jina Reader 失败时自动切换到本地解析
- 📦 批量处理：支持同时获取多个 URL
- 🎯 灵活控制：可选择强制使用特定解析方式
- 📝 Markdown 输出：自动转换为清晰的 Markdown 格式
安装
方法 1：从源码安装
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
