AcademyMCP serversData and reporting
Data and operations teams that need clean text from PDF reports, contracts or scanned files before analysis or search.
claude mcp add pdfmux -- npx -y pdfmux-mcpThird party software. By copying, downloading or installing it you accept the Academy legal notice: you are responsible for reviewing its code and permissions before use.
Loading the file...
pdfmux extracts text from PDF files and checks its own output page by page. Each page goes to the extraction backend that suits it, such as PyMuPDF, Docling, OCR or an LLM fallback, and pages with low confidence are extracted again. Pages it cannot read are flagged instead of being dropped silently.
Data and operations teams that need clean text from PDF reports, contracts or scanned files before analysis or search. pdfmux extracts text from PDF files and checks its own output page by page. Each page goes to the extraction backend that suits it, such as PyMuPDF, Docling, OCR or an LLM fallback, and pages with low confidence are extracted again. Pages it cannot read are flagged instead of being dropped silently.
Run this in your terminal: claude mcp add pdfmux -- npx -y pdfmux-mcp
Yes. The code is on GitHub (NameetP/pdfmux) under the MIT licence.
It passed our automatic scan for credential theft, hidden instructions and risky install commands. Third party open source software. Sabemos AI does not maintain it. Check the code and permissions before you connect it to company data.