page.doc/pdf-extract — Model Context Protocol (MCP) Server
Extract PDFs to Markdown, generate RAG chunks, and include cited tables. It can also publish tracked Doc Links and provide read statistics for those links. The server is identified by the slug page-doc-pdf-extract and is described as performing PDF-to-content extraction and link tracking.
🛠️ Key Features
- Extract PDFs to Markdown
- Create RAG chunks
- Provide cited tables
- Publish tracked Doc Links with read stats
🚀 Use Cases
- Converting PDF documents into Markdown for downstream processing
- Preparing RAG-ready chunks from PDFs
- Producing table citations alongside extracted content
- Tracking engagement via published Doc Links and read statistics
⚡ Developer Benefits
- Standardizes PDF extraction into Markdown
- Supports RAG workflows through extracted chunks
- Adds cited tables for traceable outputs
- Enables analytics via read stats for Doc Links
⚠️ Limitations
- No additional constraints are provided in the available server data