doc-tools-mcp
Word document reading and writing MCP implemented in Node.js
README
Word Tools MCP Server
A Model Context Protocol (MCP) server that provides AI-powered Word document manipulation capabilities. This server implements the MCP protocol to enable AI applications to create, edit, and manage Word documents through natural language interactions.
<a href="https://glama.ai/mcp/servers/q9e176vq7l"> <img width="380" height="200" src="https://glama.ai/mcp/servers/q9e176vq7l/badge" /> </a>
Features
- Full MCP protocol implementation
- Word document creation and management
- Rich text content manipulation
- Table creation and formatting
- Document layout control
- Document metadata management
- Real-time document state monitoring
Prerequisites
- Node.js 14 or higher
- Microsoft Word (optional, for advanced features)
Installation
npx @puchunjie/doc-tools-mcp
Or install globally:
npm install -g @puchunjie/doc-tools-mcp
For use as a dependency in your project:
npm install @puchunjie/doc-tools-mcp
Usage
- Start the MCP server:
npx @puchunjie/doc-tools-mcp
-
The server will start on port 8765 by default
-
Configure your AI application (e.g., Cursor, VSCode) to use the MCP server:
http://localhost:8765
MCP Tools
The server provides the following MCP functions:
-
create_document- Create a new Word document- Parameters: filePath (required), title, author
-
open_document- Open an existing Word document- Parameters: filePath (required)
-
add_paragraph- Add a paragraph to the document- Parameters: filePath (required), text (required), style, alignment
-
add_table- Add a table to the document- Parameters: filePath (required), rows (required), cols (required), headers, data
-
search_and_replace- Find and replace text in the document- Parameters: filePath (required), searchText (required), replaceText (required), matchCase
-
set_page_margins- Set document page margins- Parameters: filePath (required), top, right, bottom, left
-
get_document_info- Get document metadata- Parameters: filePath (required)
Integration with AI Applications
Cursor
- Open the Cursor configuration file
~/.cursor/mcp.json - Add the following configuration:
{
"mcpServers": {
"doc-tools-mcp": {
"command": "npx",
"args": [
"@puchunjie/doc-tools-mcp"
]
}
}
}
Or for local development version:
{
"mcpServers": {
"doc-tools-mcp": {
"command": "node",
"args": [
"/path/to/your/doc-tools-mcp/dist/mcp-server.js"
]
}
}
}
After configuration, you can use natural language to manipulate Word documents:
"Create a new document named report.docx"
"Add a heading 'Monthly Report' to report.docx"
"Insert a 4x3 table with sales data"
VSCode and Other MCP-Compatible Tools
Similar integration steps apply to other tools that support the MCP protocol. Consult your tool's documentation for specific MCP server configuration steps.
Development
To extend or modify this MCP server:
- Clone the repository:
git clone <repository-url>
cd doc-tools-mcp
- Install dependencies:
npm install
- Start in development mode:
npm run start
- Build for production:
npm run build
Adding New MCP Functions
- Add new methods in
src/services/DocumentService.ts - Register new functions in
src/mcp-server.ts - Update type definitions as needed
Configuration
- Default port: 8765 (configurable)
- Supported file types: .docx
- All file paths should be absolute or relative to the current working directory
License
MIT
Support
If you encounter any issues or have suggestions for improvements, please submit an issue on our GitHub repository.
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.