PDF Reader
Extracts text, metadata, and images from PDF files, supporting both local files and remote URLs. Processes multiple PDFs with parallel processing and natural reading order based on Y-coordinates.
5422,334 views57Local (stdio)
What it does
- Extract text from PDF pages
- Read PDF metadata and document info
- Process remote PDFs via URLs
- Extract specific page ranges
- Retrieve images from PDFs
- Handle multiple PDFs simultaneously
Best for
AI agents processing document workflowsContent analysis and extraction pipelinesDocument automation systemsResearch and data mining from PDFs
5-10x faster parallel processingY-coordinate based natural orderingWorks with local files and URLs
Tools (1)
read_pdf
Reads content/metadata from one or more PDFs (local/URL). Each source can specify pages to extract.
