MCP Server Doccreator

🚀 MCP Server (Compliant with MCP Protocol)

This server is now an MCP server compliant with the Model Context Protocol (MCP) standard. It exposes document generation capabilities via the MCP protocol, allowing integration with AI hosts such as Copilot, Cursor, and Claude Desktop.

✨ Features

MCP Features

• MCP Tool: generateDocument — Generate PDF, DOCX, PPTX, or XLSX files from prompts.
• Transport Layer: Standard input and output (local, default). Server-Sent Events (SSE) can be added for network communication if needed.
• Schema Validation: Use zod for input validation.
• Scalability: Easily add more tools, resources, or prompts.

General Features

• Document Generation: Generate PDF, Word, PowerPoint, and Excel files from AI-driven prompts.
• Image Embedding and Scaling: Insert and resize images in DOCX and PPTX files.
• Asynchronous Processing: Queue and process document generation tasks using BullMQ and Redis.
• Validation: Validate document layouts by capturing and analyzing screenshots.
• API-First: Provide RESTful endpoints for document generation, task status checking, and result downloading.
• Scalability: Modular architecture for easy addition of new file types or tools.

📦 Project Structure

src/
  app.js
  server.js
  config/
  controllers/
  middleware/
  public/
  routes/
  services/
  utils/
  workers/
temp_image/
validation-screenshots/
test-output/

🚀 Quick Start

Prerequisites

• Node.js (Recommended version v14+)
• Redis server

Installation

1. Clone the repository:

   git clone <repository-url>
   cd mcp-server
   

2. Install dependencies:

   npm install
   

3. Set up environment variables:
   • Copy .env.example to .env and fill in the required values.

Run the Server

npm start

Run Tests

npx jest src/services/fileCreation.test.js --runInBand

📚 API Endpoints

• POST /documents/generate — Request document generation (PDF, DOCX, PPTX, XLSX).
• GET /documents/generate/status/:jobId — Check task status.
• GET /documents/generate/result/:jobId — Download the generated file.

💻 File Generation and Validation

• Support AI-driven content and layout through Gemini/OpenAI function calls.
• Support image insertion and scaling in DOCX and PPTX files.
• Use screenshots (simulated or real, see aiFileValidationService) for layout validation.

💻 Usage Examples

Build and Start

npm run build
npm start

MCP Host Configuration Example (stdio)

Add the following to your host's mcp.json:

{
  "servers": {
    "your-server-name": {
      "type": "stdio",
      "command": "node",
      "args": ["server.js"]
    }
  }
}

Validate the Connection

Run the following commands to validate the connection to the MCP server:

mcp ls
mcp info your-server-name

⚠️ Important Note

• Ensure that the Redis server is correctly installed and running.
• In a production environment, it is recommended to use HTTPS and enable authentication to protect API endpoints.
• For large-scale task processing, optimize the performance parameters of BullMQ and Redis as needed.

By following the above steps, you can easily set up and run a document generation server compliant with the MCP protocol and integrate it with various AI hosts.