关于
Empower AI agents with the ability to securely read and extract information from PDF files using a single tool. Supports both local relative paths and public URLs, providing a structured JSON output via MCP. Designed for seamless use within MCP environments via `npx` or Docker, it prioritizes security through context confinement and efficient data transfer, making it ideal for integrating PDF parsing into AI agent workflows.
主要功能
- Reads full text content, specific pages, or page ranges from PDF files.
- Retrieves the total page count of a PDF.
- Processes multiple PDF sources (local paths or URLs) in a single request.
- Extracts PDF metadata (author, title, creation date, etc.).
- Securely operates within a defined project root.
- 4 GitHub stars
使用案例
- Enabling AI agents to extract specific data from PDF reports.
- Automating PDF data extraction for knowledge base creation.
- Providing a secure and controlled way for AI models to process PDF documents.
Sponsored