Pdfmux
PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MI…
- Transport
- Not stated
- Package
- —
- Registry id
- —
No install snippet on purpose. A working MCP config is a command, its arguments and an environment block — the last two are where API keys live, so this catalogue never stores them and cannot publish them. Follow the link above for the authors' own instructions.
Pdfmux routes seven extractors per page automatically. Pdfmux provides confidence scoring per page. Pdfmux automatically re-extracts failed pages with a stronger backend.
Pdfmux includes a native MCP server for AI agents like Claude and Cursor. Pdfmux is free, MIT licensed, and runs on the user's hardware. Pdfmux offers cost prediction via the pdfmux estimate command.
Pdfmux supports Arabic and RTL text with Unicode BiDi reordering and routes Arabic documents to a vision LLM. Pdfmux integrates natively with LangChain and LlamaIndex.
Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.