OfficeMCP

A Model Context Protocol (MCP) server that enables AI assistants to create, read, write, and manipulate Microsoft Office documents (Word, Excel, PowerPoint) and PDFs directly from natural language instructions.

Features

• Format-agnostic tools — unified office_* API works across all supported formats
• Format-specific tools — granular word_*, excel_*, and pptx_* tools for advanced operations
• Markdown support — write Word/PDF content using plain Markdown
• Batch operations — perform multiple document operations in a single tool call
• PDF support — create, read, watermark, and extract pages from PDFs
• Encrypted document handling — detection and support for protected Office files
• Progressive tool disclosure — tiered tool exposure keeps context lean
• Image creation — embed images in Word, PowerPoint, and Excel documents
• Image extraction — extract all embedded images from Word, PowerPoint, and PDF files as base64 data with MIME type for direct AI vision analysis (OCR, captioning)
• Rich document reading — office_read on .docx returns an ordered content list of headings, paragraphs, tables, and inline images in document sequence, preserving section context around every image

Supported Formats

Prerequisites

• .NET 10 SDK
• An MCP-compatible client (e.g., Claude Desktop, VS Code with Copilot)

Building

git clone https://github.com/your-org/OfficeMCP.git
cd OfficeMCP
dotnet build

Running

dotnet run --project OfficeMCP/OfficeMCP.csproj

The server communicates over stdio using the MCP protocol.

MCP Client Configuration

Claude Desktop

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "OfficeMCP": {
      "command": "dotnet",
      "args": [
        "run",
        "--project",
        "C:/path/to/OfficeMCP/OfficeMCP/OfficeMCP.csproj"
      ]
    }
  }
}

Or point to the compiled binary directly for faster startup:

{
  "mcpServers": {
    "OfficeMCP": {
      "command": "C:/path/to/OfficeMCP/OfficeMCP/bin/Release/net10.0/OfficeMCP.exe"
    }
  }
}

Available Tools

Consolidated Office Tools (format-agnostic)

These tools work across all supported formats and are organized into three tiers.

Tier 1 — Core (always exposed)

Tier 2 — Common

Tier 3 — Advanced

Word Tools (word_*)

Excel Tools (excel_*)

PowerPoint Tools (pptx_*)

Image Support

Creating documents with images

Images can be embedded when creating or editing documents:

Reading documents with images

Rich ordered reading (Word — default)

Calling office_read on a .docx file returns the full document as an ordered content list where each item has a Type of "heading", "paragraph", "table", or "image". Images appear immediately after their containing paragraph so the preceding headings and paragraphs provide natural section context — no separate extraction step needed.

{
  "Content": [
    { "Type": "heading",   "Text": "Q4 Financial Summary", "Level": 1 },
    { "Type": "paragraph", "Text": "Revenue grew 23% as shown in the chart below." },
    { "Type": "image",     "AltText": "Revenue chart", "MimeType": "image/png",
                           "ImageBase64": "...", "WidthPx": 640, "HeightPx": 400 },
    { "Type": "paragraph", "Text": "Figure 1: Q4 2025 revenue by region." },
    { "Type": "heading",   "Text": "Cost Analysis", "Level": 2 }
  ]
}

Pass includeImages: false to get plain text only.

Bulk image extraction

office_extract with extractType: "images" extracts all embedded images from Word, PowerPoint, and PDF files. Each result includes:

Project Structure

OfficeMCP/
├── Program.cs                          # MCP server entry point & DI setup
├── Models/
│   └── DocumentModels.cs               # Shared data models (formatting, layout, etc.)
├── Services/
│   ├── WordDocumentService.cs          # Word document logic
│   ├── ExcelDocumentService.cs         # Excel workbook logic
│   ├── PowerPointDocumentService.cs    # PowerPoint presentation logic
│   ├── PdfDocumentService.cs           # PDF creation and manipulation
│   ├── EncryptedDocumentService.cs     # Encrypted/protected document handling
│   ├── FormatDetector.cs               # File extension → format detection
│   └── MarkdownParser.cs               # Markdown → Office content conversion
└── Tools/
    ├── OfficeDocumentToolsConsolidated.cs  # Unified office_* MCP tools
    ├── WordDocumentToolsOptimized.cs       # Word-specific word_* MCP tools
    ├── ExcelDocumentToolsOptimized.cs      # Excel-specific excel_* MCP tools
    └── PowerPointDocumentToolsOptimized.cs # PowerPoint-specific pptx_* MCP tools

Dependencies

Running Tests

dotnet test OfficeMCP.Tests/OfficeMCP.Tests.csproj

License

This project is provided as-is.