TextIn OCR Server

Example Use Cases

• 1

  Extract plain text from images, PDFs, or Office files to enable search, indexing, or summarization workflows.

• 2

  Convert documents (PDFs, Word, Excel, images) into Markdown for downstream editing, publishing, or content ingestion.

• 3

  Structured information extraction (key fields and table headers) from invoices, IDs, and other documents to populate databases or trigger automated processes.

Description

TextIn OCR MCP Server provides tools to extract text from images, PDFs and Office documents, convert documents to Markdown, and automatically identify or extract specified key-value pairs and table data. It supports OCR for common image formats, PDFs, and Microsoft Office files and returns either plain text, Markdown, or structured JSON for downstream processing. The server requires a TextIn account (APP_ID and APP_SECRET) for use and notes that URLs pointing to protected resources are not supported. It is intended to help automate document processing and information extraction workflows for agents and applications.