Office文档转换服务

# Clone the repository
git clone https://github.com/Asunainlove/office-reader-mcp.git
cd office-reader-mcp

# Install in editable mode
pip install -e .

{
  "mcpServers": {
    "officereader": {
      "command": "python",
      "args": ["-m", "officereader_mcp.server"],
      "env": {
        "OFFICEREADER_CACHE_DIR": "/path/to/cache"
      }
    }
  }
}

{
  "mcpServers": {
    "officereader": {
      "command": "python",
      "args": ["-m", "officereader_mcp.server"],
      "env": {
        "OFFICEREADER_CACHE_DIR": "/path/to/cache"
      }
    }
  }
}

Convert my Excel file at D:\Reports\sales_2024.xlsx to markdown

Extract text and images from D:\Presentations\keynote.pptx

Get metadata from my document at C:\Documents\report.docx

Convert D:\Documents\report.xlsx with images

Read the markdown at D:\cache\output\report_abc12345\report_abc12345.md

List all converted documents

Clear the document cache

Get metadata from D:\Documents\presentation.pptx

What file formats does officereader support?

cache/
└── output/
    └── document_name_abc12345/
        ├── document_name_abc12345.md    # Converted markdown
        └── images/
            ├── image_001.webp           # Optimized images
            ├── slide2_image_002.webp
            └── excel_image_003.webp

OfficeReader-MCP/
├── src/officereader_mcp/
│   ├── server.py              # MCP server implementation
│   ├── converter.py           # Word converter (DocxConverter, OfficeConverter)
│   ├── excel_converter.py    # Excel to Markdown converter
│   ├── pptx_converter.py     # PowerPoint to Markdown converter
│   ├── image_optimizer.py    # Image compression utility
│   └── __init__.py           # Package initialization
├── test/
│   ├── test_converter.py     # Basic functionality tests
│   └── test_all_formats.py   # Comprehensive test suite
├── pyproject.toml            # Project configuration
└── README.md                 # Documentation

# Basic converter test
python test/test_converter.py

# Comprehensive test suite for all formats
python test/test_all_formats.py

# Test with a specific document
python test/test_converter.py path/to/your/document.docx

# Set custom cache directory
export OFFICEREADER_CACHE_DIR=/path/to/custom/cache

# Or in Windows
set OFFICEREADER_CACHE_DIR=C:\path\to\custom\cache

User: Convert my Excel file at D:\Reports\Q4_sales.xlsx

Claude: I'll convert that Excel file. Each sheet will be converted to a separate
        section in the markdown with properly formatted tables...

[Output includes all sheets as markdown tables with preserved formatting]

User: Extract all text and images from D:\Presentations\product_launch.pptx

Claude: Converting the PowerPoint presentation. I'll extract text from each slide,
        including speaker notes, along with all embedded images...

[Output includes slide-by-slide breakdown with images and notes]

User: Convert all Office documents in D:\Documents\

Claude: I'll convert each document and cache the results for quick access...

[Processes all supported files and provides summary]

# Reinstall the package
pip install -e .

# Verify cache directory is writable
ls -la /path/to/cache  # Unix/Mac
dir /path/to/cache     # Windows

# Check if images are embedded
# Use convert_document with extract_images=true explicitly

# Clone and install with dev dependencies
git clone https://github.com/Asunainlove/office-reader-mcp.git
cd office-reader-mcp
pip install -e ".[dev]"

# Run tests
python test/test_all_formats.py

# Run linting (if configured)
black src/
ruff check src/