Office Word MCP server

This server implements the Model Context Protocol (MCP) to help AI assistants create, read, and manipulate Microsoft Word documents through a standardized interface. It acts as a bridge between AI systems and Word documents, enabling rich document editing capabilities without requiring direct access to Microsoft Word.

Installation

Prerequisites

• Python 3.8 or higher
• pip package manager

Basic Installation

# Clone the repository
git clone https://github.com/GongRzhe/Office-Word-MCP-Server.git
cd Office-Word-MCP-Server

# Install dependencies
pip install -r requirements.txt

Using the Setup Script

Alternatively, use the provided setup script which handles all installation steps:

python setup_mcp.py

Configuration for Claude for Desktop

Method 1: After Local Installation

Add the server to your Claude for Desktop configuration file:

{
  "mcpServers": {
    "word-document-server": {
      "command": "python",
      "args": ["/path/to/word_mcp_server.py"]
    }
  }
}

Method 2: Using uvx Package Manager

Configure Claude for Desktop without local installation:

{
  "mcpServers": {
    "word-document-server": {
      "command": "uvx",
      "args": ["--from", "office-word-mcp-server", "word_mcp_server"]
    }
  }
}

Configuration file locations:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

Remember to restart Claude for Desktop after making changes.

Using the Word MCP Server

Once configured, you can ask Claude to perform various Word document operations:

Document Management

• Create new documents with metadata
• Extract text and analyze document structure
• View document properties and statistics
• List available documents in a directory
• Create document copies
• Merge multiple documents
• Convert Word documents to PDF

Content Creation

• Add headings with different levels
• Insert paragraphs with optional styling
• Create tables with custom data
• Add images with proportional scaling
• Insert page breaks
• Add footnotes and endnotes

Text Formatting

• Format text sections (bold, italic, underline)
• Change text color and font properties
• Apply custom styles
• Search and replace text throughout documents

Example Commands

• "Create a new document called 'report.docx' with a title page"
• "Add a heading and three paragraphs to my document"
• "Insert a 4x4 table with sales data"
• "Format the word 'important' in paragraph 2 to be bold and red"
• "Search and replace all instances of 'old term' with 'new term'"

API Reference

Document Creation and Properties

create_document(filename, title=None, author=None)
get_document_info(filename)
get_document_text(filename)
get_document_outline(filename)
list_available_documents(directory=".")
copy_document(source_filename, destination_filename=None)
convert_to_pdf(filename, output_filename=None)

Content Addition

add_heading(filename, text, level=1)
add_paragraph(filename, text, style=None)
add_table(filename, rows, cols, data=None)
add_picture(filename, image_path, width=None)
add_page_break(filename)

Text Formatting

format_text(filename, paragraph_index, start_pos, end_pos, bold=None,
            italic=None, underline=None, color=None, font_size=None, font_name=None)
search_and_replace(filename, find_text, replace_text)
delete_paragraph(filename, paragraph_index)
create_custom_style(filename, style_name, bold=None, italic=None,
                    font_size=None, font_name=None, color=None, base_style=None)

Troubleshooting

Common Issues

1. Missing Styles

   • Some documents may lack required styles for heading and table operations
   • The server will attempt to create missing styles or use direct formatting
   • For best results, use templates with standard Word styles

2. Permission Issues

   • Ensure the server has permission to read/write to the document paths
   • Use the copy_document function to create editable copies of locked documents
   • Check file ownership and permissions if operations fail

3. Image Insertion Problems

   • Use absolute paths for image files
   • Verify image format compatibility (JPEG, PNG recommended)
   • Check image file size and permissions

Debugging

Enable detailed logging by setting the environment variable:

export MCP_DEBUG=1  # Linux/macOS
set MCP_DEBUG=1     # Windows

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.