Mcp Web Reader
@zacfire
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。
Overview
What is Mcp Web Reader?
Mcp Web Reader is a Model Context Protocol (MCP) server that enables Claude and other large language models to read and parse web page content. It supports both the Jina Reader API and a local parser, with automatic fallback between them.
How to use Mcp Web Reader?
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”.
Key features of Mcp Web Reader
- 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
Use cases of Mcp Web Reader
- Reading a single web page for content extraction
- Batch fetching multiple URLs for research or comparison
- Forcing a specific parser when one engine is preferred
FAQ from Mcp Web Reader
What parsing engines does Mcp Web Reader use?
It integrates the Jina Reader API and a built-in local parser, and can automatically switch between them.
What happens if the Jina Reader API fails?
The server automatically falls back to the local parser so requests still succeed.
Can I force Mcp Web Reader to use only one parser?
Yes, dedicated tools (Workspace_url_with_jina and Workspace_url_local) let you force either engine.
How do I configure Mcp Web Reader for Claude Desktop?
Add the server entry to claude_desktop_config.json with the path to the built dist/index.js and the command node.
Does Mcp Web Reader support multiple URLs at once?
Yes, the Workspace_multiple_urls tool accepts a list of URLs for batch retrieval.
