Routes document parsing through three engines with automatic fallback: markitdown (MIT licensed, handles PDF/DOCX/XLSX/HTML), Docling (for complex tables and scanned PDFs), and LlamaParse (cloud, bring your own key). The parse tool accepts file paths or URLs and returns markdown plus the backend chain it attempted. Includes parse_to_vault for saving converted docs to your Obsidian inbox with frontmatter metadata, and interpret for piping parsed content directly into Claude with prompt cache support. The benchmark tool runs all available backends side by side so you can see latency and quality differences. Also ships a chunk_text tool with document type detection that splits markdown into retrieval chunks while respecting structure (keeps paper abstracts whole, never splits numbered manual sections). Built on FastMCP with stdio transport.