mcp-summarizer
FreeAI 摘要 MCP 服务器，支持多种内容类型：纯文本、网页、PDF 文档、EPUB 书籍、HTML 内容。
FreeFree tier
Inputs: text, url
About mcp-summarizer
MCP Content Summarizer Server is an open-source Model Context Protocol (MCP) server that provides intelligent summarization for various content types using Google's Gemini 1.5 Pro model. It supports plain text, web pages, PDF documents, EPUB books, and HTML content. Users can customize summary length, language, focus, and style (concise, detailed, bullet-points). The server is built with TypeScript and can be integrated with desktop applications via MCP configuration. Powered by 3MinTop.
Key Features
Universal content summarization using Google's Gemini 1.5 Pro model
Support for multiple content types: plain text, web pages, PDF documents, EPUB books, HTML content
Customizable summary length (default 200 characters)
Multi-language support for summaries
Smart context preservation
Multiple summary styles: concise, detailed, bullet-points
Dynamic greeting resource for testing MCP functionality
Pros & Cons
Pros
- Open source and free to use under MIT license
- Supports diverse content formats (text, URL, PDF, EPUB, HTML)
- Customizable summary parameters (length, language, focus, style)
- Leverages powerful Google Gemini 1.5 Pro model
- Easy local setup with pnpm and TypeScript
- Integrates via standard Model Context Protocol
Cons
- Requires self-hosting and manual setup
- Depends on Google Gemini API (may require API key)
- Only supports Gemini model (no model choice)
- No hosted or cloud version available
Best For
Summarizing long articles and web pagesExtracting key information from PDF documentsCreating concise summaries of EPUB ebooksGenerating bullet-point summaries for quick reviewProducing summaries in multiple languagesIntegrating with MCP-compatible desktop applications
FAQ
What content types does the summarizer support?
It supports plain text, web pages (URLs), PDF documents, EPUB books, and HTML content.
How do I integrate this MCP server with a desktop app?
Add the server configuration to your app's mcpServers object, specifying the path to the built dist/index.js file.
What parameters does the summarize tool accept?
The summarize tool accepts content (string or object), type (text, url, pdf, epub), maxLength (optional, default 200), language (optional, default 'en'), focus (optional), and style (concise, detailed, bullet-points).
Is the server free to use?
Yes, the project is open source under MIT license and free to use, but you may need your own Google Gemini API key.