This project provides a Model Context Protocol (MCP) server for programmatic interaction with Microsoft Word documents, enabling AI assistants to create, read, and manipulate .docx files. It offers a comprehensive set of tools for document management, content creation, rich text formatting, table manipulation, and document protection, serving as a bridge between AI and Word.

How It Works

The server implements the Model Context Protocol (MCP) to expose Word document operations as tools. It leverages the python-docx library for core document manipulation, abstracting its functionality into a standardized, extensible interface. This modular architecture separates concerns, allowing for easier maintenance and future enhancements, and is designed for integration with AI assistants like Claude Desktop.

Quick Start & Requirements

• Installation: pip install -r requirements.txt after cloning the repository. Alternatively, use npx -y @smithery/cli install @GongRzhe/Office-Word-MCP-Server --client claude.
• Prerequisites: Python 3.8+, pip.
• Configuration: Add server details to Claude Desktop's claude_desktop_config.json file.
• Docs: https://github.com/GongRzhe/Office-Word-MCP-Server

Highlighted Details

• Supports creating new documents, extracting text, and analyzing document structure.
• Enables rich content creation including tables, images, footnotes, and custom styles.
• Offers advanced features like document protection (password, restricted editing) and digital signatures.
• Includes text formatting, search/replace, and table formatting capabilities.

Maintenance & Community

Contributions are welcome via pull requests. The project is open source under the MIT license.

Licensing & Compatibility

MIT License. Compatible with commercial use and closed-source linking.

Limitations & Caveats

The server interacts directly with local files; users should verify operations. Missing styles in documents may lead to direct formatting or style creation attempts. Permission issues for file access might require using copy_document or adjusting file permissions. Image insertion requires compatible formats and absolute paths.