Process images by extracting text via OCR, answering visual queries, or detecting elements through the GLM-4.5V MCP Server. Specify modes like describe, ocr, qa, or detect to analyze visuals effectively.
Retrieve table structure and schema from Grist documents to understand data organization and relationships. Specify detail levels from table names to full column information for efficient data analysis.
Retrieve Bitcoin Ordinal inscription data and save images locally for analysis. Use this tool to fetch technical metadata and prepare files for OCR processing.
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.
Extracts text from images using Tesseract OCR with support for local files, URLs, and raw image bytes. It provides production-grade OCR capabilities and multi-language support through the Model Context Protocol.