mcp-process-pdf

## mcp-process-pdf PDF Document Processing Tool ## Main Features - Text Extraction: Multi-language support, retains formatting. - Image Processing: Extraction and optimization. - Table Recognition: Structured data output. - Intelligent Classification: Based on deep learning. - Similarity Analysis: Cross-language comparison. - Multi-language Support: 100+ languages. ## System Requirements - **Hardware**: 2-core CPU, 4GB RAM. - **⚙ Software**: Python 3.10+, optional CUDA support. ## Quick Start 1. Clone the repository and navigate to the directory: ```bash git clone https://github.com/saury1120/pdf-mcp.git cd pdf-mcp ``` 2. Create a virtual environment and install dependencies: ```bash uv venv source .venv/bin/activate uv pip install -r requirements.txt ``` 3. Start the service: ```bash uv run pdf_reader ``` ### Claude Desktop Configuration 1. Locate the configuration file: - macOS: `~/Library/Application Support/Claude/claude_desktop_config.json` - Windows: `%AppData%/Claude/claude_desktop_config.json` 2. Add the following configuration: ```json { "mcpServers": { "pdf_reader": { "command": "uv", "args": [ "--directory", "/path/to/pdf-mcp", # Replace with the actual path "run", "pdf_reader" ] } } } ```