docx-editor-mcp
Enables AI assistants to create, edit, and extract data from Microsoft Word documents programmatically, supporting document creation, content editing, table manipulation, parameter extraction, and template generation.
README
DOCX Editor MCP Server
A powerful Model Context Protocol (MCP) server for creating, editing, and extracting data from Microsoft Word documents (.docx). Designed for seamless integration with AI assistants like Claude Desktop, Kilocode, and other MCP-compatible clients.
📋 Table of Contents
- Features
- Installation
- Configuration
- Available Tools
- Usage Examples
- Technology Stack
- Contributing
- License
✨ Features
Document Creation & Management
- Create new documents with pre-configured professional styles (Times New Roman, 14pt, justified alignment, 1.15 line spacing)
- Load existing templates for modification
- Save documents to any specified path
Content Editing
- Add headings with automatic styling (centered, Times New Roman, 16pt)
- Add paragraphs with customizable alignment (LEFT, CENTER, RIGHT, JUSTIFY)
- Insert formatted text with bold, italic, custom font sizes, and language attributes
- Create bullet and numbered lists with automatic formatting
Document Analysis & Extraction
- Extract all document parameters as structured JSON including:
- Core properties (author, title, subject, keywords, created/modified dates)
- Custom properties (user-defined metadata)
- Document variables (for mail merge and automation)
- Section properties (margins, page size, orientation)
- Style definitions (fonts, colors, spacing, indentation)
- Numbering and list definitions
- Headers and footers content
- Table structures
Template Generation
- Apply extracted parameters to create new documents with identical formatting
- Set core properties programmatically (author, title, subject, etc.)
- Set custom properties for document metadata
Document Structure Analysis
- Get comprehensive document structure summaries
- List all headings with levels and text
- Count paragraphs and tables
- Preview document content
📦 Installation
Prerequisites
- Python 3.10 or higher
- pip package manager
Quick Start
-
Clone the repository:
git clone https://github.com/yourusername/docx-editor-mcp.git cd docx-editor-mcp -
Install dependencies:
pip install -r requirements.txt -
Verify installation:
python -c "from docx import Document; from mcp.server.fastmcp import FastMCP; print('Installation successful!')"
⚙️ Configuration
Understanding MCP Servers
Important: MCP servers communicate via stdio using JSON-RPC protocol. They are NOT meant to be run directly from the command line for interactive use. Instead, they must be launched by an MCP client.
Claude Desktop Configuration
Add the following to your Claude Desktop configuration file:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"docx-editor": {
"command": "python",
"args": ["C:\\path\\to\\docx-editor-mcp\\server.py"]
}
}
}
Kilocode / VS Code Configuration
Add to your VS Code settings or Kilocode configuration:
{
"mcp.servers": {
"docx-editor": {
"command": "python",
"args": ["/path/to/docx-editor-mcp/server.py"]
}
}
}
🔧 Available Tools
Document Creation & Management
| Tool | Description |
|---|---|
create_document(filename) |
Creates a new document with default professional styles |
save_document(filename) |
Saves the current document to specified path |
load_template(filename) |
Loads an existing document for modification |
Content Addition
Table Manipulation
| Tool | Description |
|---|---|
add_table(rows, cols, style, alignment) |
Creates a new table |
add_table_row(table_index) |
Adds a new row to a table |
add_table_column(table_index, width_pt) |
Adds a new column to a table |
set_table_cell(table_index, row, col, text, alignment, bold, italic) |
Sets cell text and basic formatting |
merge_table_cells(table_index, start_row, start_col, end_row, end_col) |
Merges a rectangular range of cells |
set_table_cell_style(table_index, row, col, shading_color, vertical_alignment) |
Sets cell background color and alignment |
set_table_borders(table_index, border_size, border_color) |
Applies custom borders to a table |
delete_table_row(table_index, row_index) |
Deletes a specific row |
delete_table_column(table_index, col_index) |
Deletes a specific column |
Parameter Extraction
| Tool | Description |
|---|---|
extract_document_parameters(filename, compact, all_styles) |
Extract ALL document parameters as JSON |
extract_core_properties(filename) |
Extract metadata (author, title, dates, etc.) |
extract_custom_properties(filename) |
Extract user-defined custom properties |
extract_document_variables(filename) |
Extract document variables for automation |
extract_section_properties(filename) |
Extract margins, page size, orientation |
extract_styles_info(filename, all_styles, compact) |
Extract style definitions |
get_document_structure(filename) |
Get headings, paragraphs, tables summary |
Template Generation
| Tool | Description |
|---|---|
apply_template_parameters(parameters_json, output_filename) |
Create document from JSON parameters |
set_core_property(property_name, value) |
Set metadata property |
set_custom_property(property_name, value) |
Set custom property |
📖 Usage Examples
Creating a New Document
Ask your AI assistant:
Create a new Word document called "report.docx" with:
- A heading "Annual Report 2024"
- A paragraph about company performance
- A bullet list with key achievements
The server will execute:
create_document("report.docx")
add_heading("Annual Report 2024", level=1)
add_paragraph("The company has shown remarkable growth this year...")
add_list_item("Revenue increased by 25%", style="List Bullet")
add_list_item("Expanded to 3 new markets", style="List Bullet")
save_document()
Extracting Document Parameters
Extract all parameters from "template.docx" and show me the styles used.
Returns structured JSON:
{
"core_properties": {
"author": "John Doe",
"title": "Company Template",
"created": "2024-01-15T10:30:00"
},
"sections": [{
"margins": {
"top_mm": 15,
"bottom_mm": 15,
"left_mm": 20,
"right_mm": 20
},
"orientation": "portrait"
}],
"styles": {
"paragraph_styles": {
"Normal": {
"font": {"name": "Times New Roman", "size_pt": 14},
"paragraph_format": {"alignment": "JUSTIFY", "line_spacing": 1.15}
}
}
}
}
Cloning a Document Template
Extract parameters from "template.docx" and create a new document "new_report.docx" with the same formatting.
params = extract_document_parameters("template.docx")
apply_template_parameters(params, "new_report.docx")
# Now add your content...
add_heading("New Report", level=1)
add_paragraph("Your content here...")
save_document()
Analyzing Document Structure
Load "document.docx" and show me its structure.
Returns:
{
"headings": [
{"index": 0, "level": "Heading 1", "text": "Introduction"},
{"index": 5, "level": "Heading 2", "text": "Methodology"}
],
"paragraphs": [
{"index": 1, "style": "Normal", "text_preview": "This document describes..."},
{"index": 2, "style": "Normal", "text_preview": "The following sections..."}
],
"tables_count": 2
}
🛠 Technology Stack
| Component | Technology |
|---|---|
| Language | Python 3.10+ |
| Protocol | Model Context Protocol (MCP) |
| MCP Framework | FastMCP |
| Document Engine | python-docx |
| Communication | JSON-RPC over stdio |
Dependencies
mcp>=1.0.0
python-docx>=0.8.11
Default Document Styles
New documents are created with professional default styling:
| Element | Style |
|---|---|
| Normal Text | Times New Roman, 14pt, Justified, 1.15 line spacing |
| Heading 1 | Times New Roman, 16pt, Centered, No bold |
| Heading 2 | Times New Roman, 16pt, Centered, No bold |
| Margins | Top/Bottom: 15mm, Left/Right: 20mm |
| First Line Indent | 12.7mm (1.27 cm) |
🤝 Contributing
Contributions are welcome! Here's how you can help:
Getting Started
- Fork the repository
- Clone your fork:
git clone https://github.com/yourusername/docx-editor-mcp.git - Create a feature branch:
git checkout -b feature/amazing-feature - Make your changes and commit:
git commit -m "Add amazing feature" - Push to your branch:
git push origin feature/amazing-feature - Open a Pull Request
Contribution Guidelines
- Follow PEP 8 style guidelines
- Add docstrings to all new functions
- Update documentation for any new features
- Test your changes thoroughly before submitting
Feature Requests & Bug Reports
- Open an issue for bug reports or feature requests
- Provide detailed descriptions and reproduction steps for bugs
- Include examples for feature requests
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
<p align="center"> Made with ❤️ for the MCP community </p>
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.