Skip to content
Back to search

mcp-summarizer

MCP Server for AI Summarization

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/0xshellming--mcp-summarizer/badge.svg)](/listings/0xshellming--mcp-summarizer)

HTML

<a href="/listings/0xshellming--mcp-summarizer"><img src="/api/listings/0xshellming--mcp-summarizer/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

1. Clone this repository 2. Install dependencies:

   pnpm install

3. Build the project:

   pnpm run build

4. Start the server:

   pnpm start

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 113 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # MCP Content Summarizer Server
  2. A Model Context Protocol (MCP) server that provides intelligent summarization capabilities for various types of content using Google's Gemini 1.5 Pro model. This server can help you generate concise summaries while maintaining key information from different content formats.
  3. <a href="https://3min.top"><img width="380" height="200" src="/public/imgs/section1_en.jpg" alt="MCP Content Summarizer Server" /></a>
  4. ## Powered by 3MinTop
  5. The summarization service is powered by [3MinTop](https://3min.top), an AI-powered reading tool that helps you understand a chapter's content in just three minutes. 3MinTop transforms complex content into clear summaries, making learning efficient and helping build lasting reading habits.
  6. ## Features
  7. - Universal content summarization using Google's Gemini 1.5 Pro model
  8. - Support for multiple content types:
  9. - Plain text
  10. - Web pages
  11. - PDF documents
  12. - EPUB books
  13. - HTML content
  14. - Customizable summary length
  15. - Multi-language support
  16. - Smart context preservation
  17. - Dynamic greeting resource for testing
  18. ## Getting Started
  19. 1. Clone this repository
  20. 2. Install dependencies:
  21. ```
  22. pnpm install
  23. ```
  24. 3. Build the project:
  25. ```
  26. pnpm run build
  27. ```
  28. 4. Start the server:
  29. ```
  30. pnpm start
  31. ```
  32. ## Development
  33. - Use `pnpm run dev` to start the TypeScript compiler in watch mode
  34. - Modify `src/index.ts` to customize server behavior or add new tools
  35. ## Usage with Desktop App
  36. To integrate this server with a desktop app, add the following to your app's server configuration:
  37. ```js
  38. {
  39. "mcpServers": {
  40. "content-summarizer": {
  41. "command": "node",
  42. "args": [
  43. "{ABSOLUTE PATH TO FILE HERE}/dist/index.js"
  44. ]
  45. }
  46. }
  47. }
  48. ```
  49. ## Available Tools
  50. ### summarize
  51. Summarizes content from various sources using the following parameters:
  52. - `content` (string | object): The input content to summarize. Can be:
  53. - Text string
  54. - URL for web pages
  55. - Base64 encoded PDF
  56. - EPUB file content
  57. - `type` (string): Content type ("text", "url", "pdf", "epub")
  58. - `maxLength` (number, optional): Maximum length of the summary in characters (default: 200)
  59. - `language` (string, optional): Target language for the summary (default: "en")
  60. - `focus` (string, optional): Specific aspect to focus on in the summary
  61. - `style` (string, optional): Summary style ("concise", "detailed", "bullet-points")
  62. Example usage:
  63. ```typescript
  64. // Summarize a webpage
  65. const result = await server.invoke("summarize", {
  66. content: "https://example.com/article",
  67. type: "url",
  68. maxLength: 300,
  69. style: "bullet-points"
  70. });
  71. // Summarize a PDF document
  72. const result = await server.invoke("summarize", {
  73. content: pdfBase64Content,
  74. type: "pdf",
  75. language: "zh",
  76. style: "detailed"
  77. });
  78. ```
  79. ### greeting
  80. A dynamic resource that demonstrates basic MCP resource functionality:
  81. - URI format: `greeting://{name}`
  82. - Returns a greeting message with the provided name
  83. ## Contributing
  84. Contributions are welcome! Please feel free to submit a Pull Request.
  85. ## License
  86. This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.