pdf-spread-viewer

pdf-spread-viewer

A simple MCP server that converts PDF double-page spreads into single images with black borders, simulating book binding/gutter for reviewing book layouts.

Category
访问服务器

README

PDF Spread Viewer MCP Server

A simple MCP (Model Context Protocol) server that converts PDF double-page spreads into single images with black borders, perfect for reviewing book layouts.

Features

  • Convert two consecutive PDF pages into one side-by-side image
  • Add black borders to simulate book binding/gutter
  • High-quality output (200 DPI)
  • Simple stdio-based MCP server (no web server needed)
  • Returns images directly in MCP responses

Installation

Prerequisites

Make sure you have Python 3.7+ and poppler installed:

# macOS
brew install poppler

# Ubuntu/Debian
sudo apt-get install poppler-utils

# Windows
# Download from: https://github.com/oschwartz10612/poppler-windows/releases

Install Python Dependencies

cd ~/projects/pdf-spread-viewer
pip install -r requirements.txt

Or manually:

pip install pdf2image Pillow

Usage

As MCP Server in Cursor

Add to your Cursor MCP configuration:

{
  "mcpServers": {
    "pdf-spread-viewer": {
      "command": "python3",
      "args": ["/Users/rmi/projects/pdf-spread-viewer/server.py"]
    }
  }
}

Then restart Cursor and use the get_spread tool:

Show me pages 14-15 of embers_final.pdf as a double-page spread

Standalone Script

You can also use it as a standalone script:

python3 server.py

Then send JSON-RPC requests via stdin:

{"jsonrpc": "2.0", "id": 1, "method": "initialize", "params": {}}
{"jsonrpc": "2.0", "id": 2, "method": "tools/list", "params": {}}
{"jsonrpc": "2.0", "id": 3, "method": "tools/call", "params": {"name": "get_spread", "arguments": {"pdf_path": "~/projects/books/dragon-fly/embers_final.pdf", "left_page": 14, "right_page": 15}}}

Tool Parameters

get_spread

Converts two PDF pages into a single side-by-side image.

Parameters:

  • pdf_path (string, required): Path to PDF file (supports ~ for home directory)
  • left_page (integer, required): Left page number (1-based)
  • right_page (integer, required): Right page number (1-based)
  • border_width (integer, optional): Border width in pixels (default: 2)

Returns:

  • PNG image showing both pages side-by-side with black borders

Example Output

The tool creates images that look like this:

┌──────────────────────────────────────────────┐
│  ┌──────────┐ │ ┌──────────┐                │
│  │ Page 14  │ │ │ Page 15  │                │
│  │  (text)  │ │ │  (image) │                │
│  └──────────┘ │ └──────────┘                │
└──────────────────────────────────────────────┘
     Left page      Right page

The black border in the center simulates the book's gutter/binding.

License

MIT License - feel free to use and modify!

Contributing

This is an open-source project. PRs welcome!

Repository: https://github.com/yourusername/pdf-spread-viewer (update with actual URL)

Troubleshooting

Error: "pdf2image not found"

pip install pdf2image Pillow

Error: "poppler not found"

brew install poppler  # macOS

Error: "PDF file not found"

  • Use absolute paths or ~ for home directory
  • Check file exists with ls -la path/to/file.pdf

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选