Document Generator MCP
Enables AI agents to generate professional Word and PDF documents with support for Markdown, syntax highlighting, and smart pagination. It features automatic JSON detection and responsive A4 formatting for creating high-quality technical reports and manuals.
README
Document Generator MCP
An MCP (Model Context Protocol) server to generate professional Word (.docx) and PDF documents from any AI agent that supports MCP, including Claude Desktop, Amazon Q Developer, Cline, Continue, and others.
๐ Features
- โ Generate Word documents (.docx)
- โ Generate PDF documents
- โ Auto-detect JSON blocks (no backticks needed!) ๐
- โ Professional syntax highlighting (VS Code Dark theme)
- โ Smart pagination (no content cuts between pages)
- โ 100% responsive formatting (respects A4 margins)
- โ Markdown support (headings, lists, bold, italic, code blocks)
- โ Automatic professional formatting
- โ Metadata (author, creation date)
๐ฆ Installation
Via NPX (Recommended)
npx document-generator-mcp@latest
Via NPM Global
npm install -g document-generator-mcp
โ๏ธ Configuration
Claude Desktop
-
Locate the configuration file:
- Linux:
~/.config/claude-desktop/claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
- Linux:
-
Add this configuration:
{
"mcpServers": {
"document-generator": {
"command": "npx",
"args": ["--yes", "--cache", "/tmp/.npx-cache", "document-generator-mcp@latest"]
}
}
}
- Restart Claude Desktop
Amazon Q Developer
- Open VS Code with Amazon Q extension
- Access Amazon Q settings
- Add the MCP server:
{
"mcpServers": {
"document-generator": {
"command": "npx",
"args": ["--yes", "--cache", "/tmp/.npx-cache", "document-generator-mcp@latest"]
}
}
}
Other MCP Agents (Cline, Continue, etc.)
For other agents that support MCP, add the server configuration:
{
"name": "document-generator",
"command": "npx",
"args": ["--yes", "--cache", "/tmp/.npx-cache", "document-generator-mcp@latest"]
}
Check your agent's specific documentation for configuration details.
๐ฏ How to Use
After configuration, you can use natural commands in any MCP agent:
Example Prompts
- "Create a Word document about sales analysis"
- "Generate a PDF report about the project"
- "Make a technical manual in Word and PDF"
- "Create API documentation in Word format"
- "Document this JavaScript code with examples"
Available Tools
gerar_documento_word: Creates Word documents, PDF, or bothgerar_documento_pdf: Creates PDF documents only
๐ Supported Formatting
The MCP automatically processes:
Markdown
# Heading 1โ Heading 1 (20pt)## Heading 2โ Heading 2 (16pt, blue)### Heading 3โ Heading 3 (14pt)#### Heading 4โ Heading 4 (12pt)- Itemโ Bulleted list1. Itemโ Numbered list**text**โ Bold text*text*โ Italic text***text***โ Bold + Italic`code`โ Inline code> quoteโ Blockquote---โ Horizontal line
Code Blocks
```javascript
async function example() {
const data = await fetch('api.com');
return data.json();
}
```
Auto-Detected JSON (New in v1.0.9!)
JSON objects and arrays are automatically detected and formatted as code blocks:
{
"status": "success",
"data": {
"users": [
{"id": 1, "name": "John"}
]
}
}
No need for ``` backticks! Just paste your JSON and it will be automatically formatted with syntax highlighting.
Syntax Highlighting Colors (VS Code Dark theme):
- ๐ฃ Keywords:
async,function,const,await, etc. (#C586C0) - ๐ Strings:
"text",'text'(#CE9178) - ๐ข Comments:
// comment,/* block */(#6A9955) - ๐ข Numbers:
42,3.14,0xFF(#B5CEA8) - ๐ก Functions:
fetch,console.log(#DCDCAA) - ๐ต Types/Classes:
Promise,Array(#4EC9B0)
๐จ Features Highlights
Professional Syntax Highlighting
- Dark background (#1E1E1E) for code blocks
- VS Code Dark theme colors
- Language indicator header
- Automatic line wrapping
Smart Pagination
- Code blocks never split between pages
- Headings kept with following content
- Automatic page breaks when needed
- Consistent spacing
Responsive Formatting
- All content respects A4 margins
- Automatic line breaks for long text
- Proper width control for all elements
- No content overflow
๐งช Testing
To test if it's working:
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' | npx document-generator-mcp@latest
Expected output: List of available tools (gerar_documento_word, gerar_documento_pdf)
๐ง Troubleshooting
Error "use strict: not found"
If you get this error, npm is using an old cached version. Solutions:
- Use this optimized configuration:
{
"mcpServers": {
"document-generator": {
"command": "npx",
"args": ["--yes", "--cache", "/tmp/.npx-cache", "document-generator-mcp@latest"]
}
}
}
- Or clear the cache:
npm cache clean --force
rm -rf ~/.npm/_npx
Documents not generating
- Check if
generated_documents/folder exists - Verify Node.js version (18+ required)
- Check MCP server logs in your agent
๐ Generated Files
Documents are saved in ./generated_documents/ with unique timestamps.
Example: api_documentation_1759715959772.docx
๐ค Compatible Agents
This MCP works with any agent that implements the Model Context Protocol:
- โ Claude Desktop - Full native support
- โ Amazon Q Developer - Support via VS Code
- โ Cline (VS Code) - VS Code extension
- โ Continue - Code assistant with MCP
- โ Other MCP agents - Any compatible implementation
๐ค Contributing
Contributions are welcome! Open issues or pull requests on GitHub.
Development Setup
git clone https://github.com/thiagotw10/document-generator-mcp.git
cd document-generator-mcp
npm install
npm run build
๐ License
MIT License - see LICENSE file for details.
๐ Links
- NPM Package: https://www.npmjs.com/package/document-generator-mcp
- GitHub Repository: https://github.com/thiagotw10/document-generator-mcp
- MCP Documentation: https://modelcontextprotocol.io
- Amazon Q MCP Guide: https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/qdev-mcp.html
โ ๏ธ Requirements
- Node.js: 18+ required
- Platforms: Linux, macOS, Windows
- MCP Support: Any agent implementing Model Context Protocol
๐ Changelog
v1.0.9 (Latest)
- โ Auto-detect JSON blocks - No need for ``` backticks around JSON
- โ Automatically formats JSON objects and arrays as code blocks
- โ Validates JSON syntax before formatting
- โ Applies syntax highlighting to detected JSON
- โ Works in both Word and PDF documents
v1.0.8
- โ English documentation for international audience
- โ Improved README structure
v1.0.7
- โ Professional syntax highlighting in PDF (VS Code Dark theme)
- โ 100% responsive formatting (respects A4 margins)
- โ Smart pagination (no content cuts)
- โ Improved spacing after code blocks
- โ Visual parity between Word and PDF
Made with โค๏ธ by Thiago Oliveira
Transform natural language into professional documents with AI!
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.