Enables local, read-only extraction of text and structure from PDF, DOCX, PPTX, SVG, and PNG files, including OCR for images, directory tree and metadata reporting, with strict path isolation and audit logging.
Classifies PDFs (text-based vs scanned vs image vs mixed), extracts text, and converts to clean Markdown over Streamable HTTP MCP. Supports remote PDFs via URL or base64, with optional page restriction and OCR fallback detection.
Document-engineering MCP tool server providing tools for PDF, Office, Images, and Archives extraction and conversion. It never mutates source files and requires local tesseract for OCR.
MCP server that parses aviation accident reports (PDF/DOCX/TXT) and injects their content into extraction prompt templates for knowledge graph construction.