高性能 PDF 文档处理服务,支持文本、图片、表格提取及高级分析。
- 📜 文本提取:多语言支持,保留格式。
- 🖼️ 图片处理:提取与优化。
- 📊 表格识别:结构化数据输出。
- 🧠 智能分类:基于深度学习。
- 🔍 相似度分析:跨语言比较。
- 🌐 多语言支持:100+ 种语言。
- 🖥️ 硬件:2 核 CPU,4GB 内存。
- ⚙️ 软件:Python 3.10+,可选 CUDA 支持。
- 🗂️ 克隆仓库并进入目录:
git clone https://github.com/saury1120/pdf-mcp.git cd pdf-mcp - 🛠️ 创建虚拟环境并安装依赖:
uv venv source .venv/bin/activate uv pip install -r requirements.txt ▶️ 启动服务:uv run pdf_reader
- 找到配置文件:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%AppData%/Claude/claude_desktop_config.json
- macOS:
- 添加以下配置:
{
"mcpServers": {
"pdf_reader": {
"command": "uv",
"args": [
"--directory",
"/path/to/pdf-mcp", # 替换为实际路径
"run",
"pdf_reader"
]
}
}
}A high-performance PDF document processing service supporting text, image, table extraction, and advanced analysis.
- 📜 Text Extraction: Multilingual support, retains formatting.
- 🖼️ Image Processing: Extraction and optimization.
- 📊 Table Recognition: Structured data output.
- 🧠 Intelligent Classification: Based on deep learning.
- 🔍 Similarity Analysis: Cross-language comparison.
- 🌐 Multilingual Support: 100+ languages.
- 🖥️ Hardware: 2-core CPU, 4GB RAM.
- ⚙️ Software: Python 3.10+, optional CUDA support.
- 🗂️ Clone the repository and enter the directory:
git clone https://github.com/saury1120/pdf-mcp.git cd pdf-mcp - 🛠️ Create a virtual environment and install dependencies:
uv venv source .venv/bin/activate uv pip install -r requirements.txt ▶️ Start the service:uv run pdf_reader
{
"mcpServers": {
"pdf_reader": {
"command": "uv",
"args": [
"--directory",
"/path/to/pdf-mcp", # 替换为实际路径
"run",
"pdf_reader"
]
}
}
}