The Simple Document Processing MCP Server provides comprehensive document processing capabilities for various file formats:
Read content from PDF, DOCX, TXT, HTML, CSV, and Excel files
Convert documents between formats (DOCX to PDF/HTML, HTML to TXT/Markdown, Excel to JSON, and between Markdown/HTML/XML/JSON)
PDF manipulation: Merge multiple PDFs or split PDFs by page ranges
Text processing: Split text by lines/delimiters, compare files, format text, and convert between encodings (UTF-8, Big5, GBK)
HTML processing: Clean HTML, extract resources (images, links, videos), format HTML, and convert to plain text or Markdown
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Simple Document Processing MCP Server convert my report.docx to PDF and clean up the formatting"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A powerful Model Context Protocol (MCP) server providing comprehensive document processing capabilities.
Read DOCX, PDF, TXT, HTML, CSV
DOCX to HTML/PDF conversion
HTML to TXT/Markdown conversion
PDF manipulation (merge, split)
Multi-encoding transfer support (UTF-8, Big5, GBK)
Text formatting and cleaning
Text comparison and diff generation
Text splitting by lines or delimiter
HTML cleaning and formatting
Resource extraction (images, links, videos)
Structure-preserving conversion
Related MCP server: docx-mcp
To install Document Processing Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @cablate/mcp-doc-forge --client claudenpm install -g @cablate/mcp-doc-forgemcp-doc-forgeClick "+ Add MCP Server" in Dive Desktop
Copy and paste this configuration:
{
"mcpServers": {
"searxng": {
"command": "npx",
"args": [
"-y",
"@cablate/mcp-doc-forge"
],
"enabled": true
}
}
}Click "Save" to install the MCP server
MIT
Welcome community participation and contributions! Here are ways to contribute:
⭐️ Star the project if you find it helpful
🐛 Submit Issues: Report problems or provide suggestions
🔧 Create Pull Requests: Submit code improvements
If you have any questions or suggestions, feel free to reach out:
📧 Email: reahtuoo310109@gmail.com
📧 GitHub: CabLate
🤝 Collaboration: Welcome to discuss project cooperation
📚 Technical Guidance: Sincere welcome for suggestions and guidance
Read content from non-image document-files at specified paths, supporting various file formats: .pdf, .docx, .txt, .html, .csv
Inputs: filePath (required).
Convert DOCX to HTML while preserving formatting
Inputs: inputPath (required), outputDir (required).
Convert DOCX files to PDF format
Inputs: inputPath (required), outputPath (required).
Read Excel file and convert to JSON format while preserving structure
Inputs: inputPath (required), includeHeaders.
Convert between different document formats (Markdown, HTML, XML, JSON)
Inputs: input (required), fromFormat (required), toFormat (required).
Clean HTML by removing unnecessary tags and attributes
Inputs: inputPath (required), outputDir (required).
Extract all resources (images, videos, links) from HTML
Inputs: inputPath (required), outputDir (required).
Format and beautify HTML code
Inputs: inputPath (required), outputDir (required).
Convert HTML to Markdown format
Inputs: inputPath (required), outputDir (required).
Convert HTML to plain text while preserving structure
Inputs: inputPath (required), outputDir (required).
Merge multiple PDF files into one
Inputs: inputPaths (required), outputDir (required).
Split a PDF file into multiple files
Inputs: inputPath (required), outputDir (required), pageRanges (required).
Compare two text files and show differences
Inputs: file1Path (required), file2Path (required), outputDir (required).
Convert text between different encodings
Inputs: inputPath (required), outputDir (required), fromEncoding (required), toEncoding (required).
Format text with proper indentation and line spacing
Inputs: inputPath (required), outputDir (required).
Split text file by specified delimiter or line count
Inputs: inputPath (required), outputDir (required), splitBy (required), value (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 16 tools
Each tool targets a distinct operation: reading various formats, specific conversions (docx, html, pdf, text), and manipulations. There is no overlap in purpose; even similar conversions like html_to_markdown and html_to_text are clearly differentiated.
All tool names follow the verb_noun pattern (e.g., document_reader, docx_to_html, text_splitter) using consistent snake_case. The naming is predictable and easy to understand.
With 16 tools, the count is slightly above the typical range of 3-15, but it is justified by the breadth of document formats and operations covered, making it reasonable for the server's purpose.
The tool set covers reading, converting, and manipulating common document formats (PDF, DOCX, HTML, text, Excel). Minor gaps exist, such as missing direct docx-to-text conversion (though document_reader can read docx), but the overall surface is comprehensive for most document processing needs.
Automate enterprise-grade documents from templates, merge and 100+ conversions: PDF, Office, HTML.
Composable APIs for document extraction, image transformation, and document & sheet generation.
Document conversion and OCR for AI agents: PDF, Office docs, images to text.
Convert, create and edit Word, PowerPoint, Excel and PDF documents from any AI agent.
