Extract targeted information from files without loading entire contents. Ask specific questions about text, code, images, or PDFs to get precise answers while minimizing context usage.
Break down large PDF files into smaller chunks to manage memory constraints. Define page range, chunk size, and output summary for efficient processing of PDFs over 50MB.
Locate and analyze PDF files based on content similarity, using repeating substring patterns or text analysis, to identify related documents within a specified directory.
Enables AI agents to safely explore directories, read files, search content by pattern or filename, and edit files with checksum verification and dry-run preview within sandboxed filesystem access.
mcp using PyPDF2 to:
• merge-pdfs
• extract-pages
• search-pdfs
• merge-pdfs-ordered (merge in user spec. order)
• find-related-pdfs (regex extracted text for related PDF files)