Extract figures, tables, and equations from PDF documents using layout detection. Returns base64-encoded images with metadata for academic papers or any PDF URL.
Extract figures, tables, and equations from PDF documents using layout detection. Returns base64-encoded images with metadata from academic papers or any PDF URL.
Extract figures, tables, and equations from PDF documents using layout detection. Returns base64-encoded images of detected elements with metadata from academic papers or any PDF URL.
Process documents to import annotations, flatten content, perform OCR, rotate pages, add watermarks, apply redactions, and convert to multiple formats including PDF, images, JSON, and Office files.
Enables integration between MCP clients and the Handwriting OCR service, allowing users to upload images and PDF documents, check processing status, and retrieve OCR results as Markdown.
A Model Context Protocol server that generates lightweight ASCII charts directly in terminal environments, supporting line charts, bar charts, scatter plots, histograms, and sparklines without GUI dependencies.