Agent♥︎Age
Catalog

PDF to Markdown & Document Parser

Official

by fernandoguiraud16-coder · HTML

Convert PDF, Word, Excel and scanned documents to Markdown, tables and RAG chunks. OCR.

document-to-markdown-tables MCP Server

This MCP server converts documents into Markdown, tables, and retrieval-ready RAG chunks. It supports input formats including PDF, Word, Excel, and scanned documents, using OCR for scanned content. The server description focuses on extracting structured text and producing Markdown outputs suitable for downstream processing.

🛠️ Key Features

  • Convert PDF, Word, Excel, and scanned documents
  • Output Markdown, tables, and RAG chunks
  • OCR support for scanned documents

🚀 Use Cases

  • Transform document files into Markdown for editing or publishing
  • Extract tabular content into table-formatted output
  • Create RAG chunks from documents for retrieval workflows

⚡ Developer Benefits

  • Structured outputs (Markdown, tables, RAG chunks) from common office and document formats
  • OCR-enabled processing for scanned documents

⚠️ Limitations

  • Not specified beyond the listed supported formats (PDF, Word, Excel, scanned) and output types (Markdown, tables, RAG chunks)

Topics

ai-agentsapifygoogle-newsgoogle-trendsmcppdf-table-extractionpdf-to-markdownpythonragtech-stacktranscriptionweb-scrapingwhisperwhois