mcp-doc-forge
If you are the rightful owner of mcp-doc-forge and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A powerful Model Context Protocol (MCP) server providing comprehensive document processing capabilities.
The Simple Document Processing MCP Server is designed to offer robust document processing functionalities. It supports reading various document formats such as DOCX, PDF, TXT, HTML, and CSV. The server also provides document conversion capabilities, allowing users to convert DOCX files to HTML or PDF, and HTML files to TXT or Markdown. Additionally, it offers PDF manipulation features like merging and splitting. Text processing is another key feature, with support for multi-encoding transfers, text formatting, cleaning, comparison, and diff generation. The server can also split text by lines or delimiters. For HTML processing, it includes cleaning and formatting, resource extraction, and structure-preserving conversion. The server can be installed via Smithery or manually using npm, and it is compatible with platforms like Dive Desktop.
Features
- Document Reader: Read DOCX, PDF, TXT, HTML, CSV
- Document Conversion: DOCX to HTML/PDF conversion, HTML to TXT/Markdown conversion, PDF manipulation (merge, split)
- Text Processing: Multi-encoding transfer support (UTF-8, Big5, GBK), text formatting and cleaning, text comparison and diff generation, text splitting by lines or delimiter
- HTML Processing: HTML cleaning and formatting, resource extraction (images, links, videos), structure-preserving conversion
