Textin MCP Server
OfficialPerforms OCR on images, PDFs, and Word documents to extract text, convert documents to Markdown format, and extract structured information from various document types.
28171 views8Local (stdio)
What it does
- Extract text from images and documents via OCR
- Convert PDFs and Office documents to Markdown
- Extract structured information and key-value pairs from documents
- Process documents from local files or HTTP/HTTPS URLs
- Handle multiple file formats including PDF, Word, Excel, and common image formats
Best for
Content creators digitizing printed materialsDevelopers building document processing workflowsResearchers extracting data from scanned documentsTeams converting legacy documents to modern formats
Supports both local files and web URLsMultiple output formats (plain text, Markdown, structured JSON)
