Office Mcp

by claude-office-skills9c4c7d5cd281MIT499 starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 8 months ago

MCP server with 39 tools for Word, Excel, PowerPoint, PDF, OCR operations

AI-generated overview

An MCP server exposing 39 tools for Word, Excel, PowerPoint, PDF and OCR document operations.

What it does
This skill documents an MCP server that provides 39 tools for office document work, grouped into PDF, spreadsheet, document, conversion and presentation categories. It covers extracting text and tables from PDFs, merging, splitting, compressing and watermarking PDFs, filling PDF forms, and running OCR on scanned PDFs and images. It also creates and reads Excel and Word files, fills DOCX templates, builds PowerPoint decks, and converts between formats such as XLSX, CSV, JSON, Markdown, DOCX, PDF and HTML.
When to use it
Use it when an agent needs to read, create, convert or manipulate office files such as PDFs, spreadsheets, Word documents or slide decks. It suits tasks like extracting text from a PDF, merging Word documents, generating a presentation, or converting a spreadsheet to CSV.
Requirements
Requires Node.js and npm to install and build the MCP server, plus configuration in the MCP client (for example Claude Desktop). Depends on packages including pdf-parse, pdf-lib, tesseract.js, xlsx, mammoth, docx, docxtemplater, pizzip, pptxgenjs, jszip, turndown and marked. Some conversions (docx_to_pdf, html_to_pdf) need an external tool. The skill itself ships instructions only, with no scripts.

Office MCP Server

Overview

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 Categories

PDF Tools (10)

ToolDescription
extract_text_from_pdfExtract text content, supports page selection
extract_tables_from_pdfExtract table data from PDFs
merge_pdfsMerge multiple PDFs into one
split_pdfSplit PDF by page ranges
compress_pdfReduce PDF file size
add_watermark_to_pdfAdd text/image watermarks
fill_pdf_formFill PDF form fields
get_pdf_metadataGet PDF properties and metadata
ocr_pdfOCR on scanned PDFs (multi-language)
ocr_imageOCR on image files (PNG, JPG, TIFF, etc.)

Spreadsheet Tools (7)

ToolDescription
read_xlsxRead Excel files with sheet/range selection
create_xlsxCreate multi-sheet Excel files
analyze_spreadsheetStatistical analysis (min/max/mean/median)
apply_formulaApply Excel formulas to cells
create_chartGenerate chart configurations
pivot_tableCreate pivot tables with aggregation
xlsx_to_jsonConvert Excel to JSON

Document Tools (6)

ToolDescription
extract_text_from_docxExtract text from Word documents
create_docxCreate DOCX with headings, lists, tables
fill_docx_templateFill templates with {{placeholders}}
analyze_document_structureAnalyze headings, tables, word count
insert_table_to_docxInsert tables into documents
merge_docx_filesMerge multiple Word documents

Conversion Tools (9)

ToolDescription
xlsx_to_csvConvert Excel to CSV
csv_to_xlsxConvert CSV to Excel
json_to_xlsxConvert JSON arrays to Excel
docx_to_mdConvert Word to Markdown
md_to_docxConvert Markdown to Word
pdf_to_docxConvert PDF to Word (text extraction)
docx_to_pdfConvert Word to PDF (external tool required)
html_to_pdfConvert HTML to PDF (external tool required)
batch_convertBatch convert multiple files

Presentation Tools (7)

ToolDescription
create_pptxCreate PowerPoint with themes
extract_from_pptxExtract text and images from PPTX
md_to_pptxConvert Markdown to slides
add_slideAdd slides to existing presentations
update_slideUpdate slide content
pptx_to_htmlConvert to reveal.js HTML
get_pptx_outlineGet presentation structure

Installation

1. Clone and Build

bash
cd mcp-servers/office-mcpnpm installnpm run build

2. Configure Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

json
{  "mcpServers": {    "office-mcp": {      "command": "/usr/local/bin/node",      "args": ["/path/to/claude-office-skills/mcp-servers/office-mcp/dist/index.js"]    }  }}

3. Restart Claude Desktop

Example Prompts

  • "Read the Excel file at ~/Documents/sales.xlsx"
  • "Create a PowerPoint with 5 slides about AI trends"
  • "Extract text from this PDF and convert to Markdown"
  • "Merge these 3 Word documents into one"
  • "Analyze the data in this spreadsheet"

Dependencies

pdf-parse, pdf-lib       - PDF operationstesseract.js             - OCR (pure JavaScript, no native binary needed)xlsx                     - Excel operationsmammoth, docx            - Word operationsdocxtemplater, pizzip    - Template fillingpptxgenjs, jszip         - PowerPoint operationsturndown, marked         - Markdown conversion

Supported OCR Languages

  • eng - English
  • chi_sim - Simplified Chinese
  • chi_tra - Traditional Chinese
  • jpn - Japanese
  • kor - Korean
  • fra - French
  • deu - German
  • spa - Spanish

Resources

Source and attribution

Source:claude-office-skills/skillsinoffice-mcpat commit9c4c7d5

License: MIT

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal