"PDM" matching MCP servers:

Enables local LLMs to match lesson summaries or syllabus topics against PDF textbooks and manuals, returning the exact page ranges relevant to each topic along with brief explanations of why they matter. Runs entirely offline via Ollama embeddings and reasoning plus Tesseract OCR for scanned or image-only pages, so multi-hundred-page documents can be searched privately without API keys or cloud credits.

Enables people and AI to read the same PDFs, arXiv papers, and GitHub documentation/code together by preserving source identity, page or line locations, and selected text so the current chat can explain the material in context.