
This is a proper MCP server that gives Claude 39 actual tools for Office documents, not just API wrappers. You get PDF extraction and merging, Excel analysis with formulas and pivot tables, Word template filling, and PowerPoint generation from Markdown. The OCR runs in pure JavaScript via Tesseract, so no binary dependencies to wrestle with. It's built for the kind of work where you need to process reports, merge docs, or pull data from spreadsheets without opening Office apps. The template filling and batch conversion tools are the standout pieces here. Works with Sonnet and Opus 4, requires Node.js and a quick config edit to Claude Desktop.
$ npx -y skills add claude-office-skills/skills --skill office-mcp --agent claude-codeInstalls into .claude/skills of the current project.
A complete MCP (Model Context Protocol) server providing 39 tools for Office document operations. Implemented in TypeScript/Node.js with real functionality (not placeholders).
| Tool | Description |
|---|---|
extract_text_from_pdf | Extract text content, supports page selection |
extract_tables_from_pdf | Extract table data from PDFs |
merge_pdfs | Merge multiple PDFs into one |
split_pdf | Split PDF by page ranges |
compress_pdf | Reduce PDF file size |
add_watermark_to_pdf | Add text/image watermarks |
fill_pdf_form | Fill PDF form fields |
get_pdf_metadata | Get PDF properties and metadata |
ocr_pdf | OCR on scanned PDFs (multi-language) |
ocr_image | OCR on image files (PNG, JPG, TIFF, etc.) |
Sponsors