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.
Convert PDF files from URLs into Markdown format, supporting single or multiple URLs. Optionally enable OCR for extracting text from scanned documents.
Retrieve detailed table structure information, including columns, data types, and constraints, for any table within a Vertica database. Specify table name and schema to generate structure data.
Process images in a directory with operations like enhancing, OCR, resizing, and deduplication, returning results in JSON format for streamlined image management.
Retrieve comprehensive schema details, column definitions, data types, and metadata for a specified table in CockroachDB. This tool enables accurate interpretation of table structures to support precise query formulation and data manipulation.
A web scraper for financial table data that implements the Model Context Protocol, allowing users to query stock data from multiple Chinese financial websites including THS, TDX, and EastMoney.
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.