PDF Reader
Securely reads and extracts text, metadata, and page counts from PDF files (local or URL) for use by AI agents.
About
Empower AI agents to securely read and extract information from PDF files using this Model Content Protocol (MCP) server. It allows for extracting full text, specific pages, metadata, and page counts from both local files and public URLs. Designed for seamless integration into MCP environments, it prioritizes security by confining file access to the project root directory and provides structured JSON output for easy parsing.
Key Features
- Extract full text, specific pages, metadata, and page count
- Easy integration via npm or Docker
- Handles both local relative paths and public URLs
- 20 GitHub stars
- Secure PDF parsing within a confined project context
- Structured JSON output for easy agent parsing
Use Cases
- Building knowledge bases from PDF content
- Automated extraction of metadata from PDF documents
- Enabling AI agents to process information from PDF reports
Sponsored