PDF-to-Markdown extraction that audits its own output and flags any extractor's silent drops.
The PDF parser that doesn’t break your RAG pipeline. · Smart PDF-to-Markdown router. 7 extractors + BYOK vision LLMs (Gemini, Gemma 4, Claude, GPT-4o, Mistral, Ollama). Per-page confidence scoring. Smart result cache. Streaming output. Watch mode. Arabic / RTL support. Built-in MCP server. Zero config. · Two things that cost nothing and need no account · Most RAG pipelines fail before they reach the model · How it works · Three lines of Python
pypi:pdfmux
| Type | MCP server |
| Section | MCP servers |
| Pricing | free |
| Platform | Command line |
| Systems | cli, api |
| Hosting | local |
| Install | mcp |
| Who for | разработчики, команды и бизнес |
| Protocols | mcp |
| Site language | en |
| GitHub | NameetP/pdfmux |
| Launched | 2026-07-27 |