Report Builder MCP Server

An MCP (Model Context Protocol) server for formatting AI agent outputs into professional reports, emails, and documents. Built for the AI Operations Platform.

🎯 Purpose

This MCP server helps you:

• ✅ Format agent outputs into email-ready templates
• ✅ Create professional HTML reports with branding
• ✅ Generate executive summaries from long content
• ✅ Validate output quality (detect generic AI language)
• ✅ Apply client-specific branding to outputs

🚀 Quick Start

Option 1: Use with Replit (Recommended for Testing)

1. Fork this to Replit:

   • Go to Replit.com
   • Click "Create Repl" → Import from GitHub
   • Or create a new Node.js repl and copy these files

2. Install dependencies:

   npm install
   

3. Test the server:

   npm test
   

4. Run HTTP API (for platform integration):

   npm install express
   node http-server.js
   

Option 2: Deploy to Railway/Render

1. Push to GitHub
2. Connect to Railway.app or Render.com
3. Set build command: npm install
4. Set start command: node http-server.js
5. Deploy!

Option 3: Use with Claude Desktop

1. Install locally:

   git clone <your-repo>
   cd report-builder-mcp
   npm install
   

2. Add to Claude Desktop config:

   Mac: ~/Library/Application Support/Claude/claude_desktop_config.json

   Windows: %APPDATA%/Claude/claude_desktop_config.json

   {
     "mcpServers": {
       "report-builder": {
         "command": "node",
         "args": ["/absolute/path/to/report-builder-mcp/server.js"]
       }
     }
   }
   

3. Restart Claude Desktop

🛠️ Available Tools

1. create_email_template

Converts agent output into email-ready format.

Input:

{
  "content": "Q4 revenue exceeded expectations by 15%...",
  "recipient_name": "John Smith",
  "subject": "Q4 Performance Report",
  "sender_name": "Audrey - Financial Analyst",
  "branding": "TechCorp Analytics",
  "include_disclaimer": true
}

2. format_report_html

Creates professional HTML report with sections and styling.

Input:

{
  "title": "Quarterly Analysis Report",
  "content": "Main report content...",
  "sections": [
    {
      "title": "Executive Summary",
      "content": "Key findings..."
    }
  ],
  "summary": "Brief overview...",
  "branding": "Company Name"
}

3. validate_output_quality

Checks agent output for generic AI language and specialization.

Input:

{
  "content": "Your agent's output here...",
  "expected_role": "legal assistant",
  "check_tone": true
}

Output:

{
  "quality_score": 85,
  "status": "GOOD",
  "issues": [],
  "suggestions": [],
  "content_length": 245
}

4. create_executive_summary

Condenses long content into key points.

Input:

{
  "full_content": "Long detailed content...",
  "max_points": 5,
  "include_recommendations": true
}

5. add_branding

Applies client-specific branding to content.

Input:

{
  "content": "Your content here...",
  "client_id": "client-123",
  "brand_elements": {
    "primary_color": "#0066cc",
    "company_name": "TechCorp",
    "tagline": "Excellence in AI"
  }
}

🌐 HTTP API Usage

If you're running the HTTP server (node http-server.js), you can call tools via REST API:

Health Check

curl http://localhost:3000/health

List Tools

curl http://localhost:3000/tools

Format Email (Convenience Endpoint)

curl -X POST http://localhost:3000/format-email \
  -H "Content-Type: application/json" \
  -d '{
    "content": "Q4 revenue exceeded expectations...",
    "recipient": "John Smith",
    "subject": "Q4 Report",
    "sender": "Audrey"
  }'

Check Quality (Convenience Endpoint)

curl -X POST http://localhost:3000/check-quality \
  -H "Content-Type: application/json" \
  -d '{
    "content": "As an AI, I cannot provide legal advice...",
    "role": "legal assistant"
  }'

Execute Any Tool

curl -X POST http://localhost:3000/tools/create_executive_summary \
  -H "Content-Type: application/json" \
  -d '{
    "full_content": "Your long content here...",
    "max_points": 5
  }'

🔗 Integration with Your Platform

N8N Workflow Integration

Create an N8N workflow:

1. Webhook Trigger - Receives data from your AI agent
2. HTTP Request Node - Calls this MCP API
   • Method: POST
   • URL: https://your-deployed-mcp.com/tools/create_email_template
   • Body: Agent output data
3. Process Response - Format the result
4. Return to Platform - Send formatted output back

Example N8N HTTP Request:

{
  "method": "POST",
  "url": "{{ $env.MCP_API_URL }}/format-email",
  "body": {
    "content": "{{ $json.agent_output }}",
    "recipient": "{{ $json.recipient_name }}",
    "subject": "{{ $json.subject }}",
    "sender": "{{ $json.agent_name }}"
  }
}

Direct Platform Integration

If your platform supports HTTP calls:

// In your platform's agent workflow
const response = await fetch('https://your-mcp-api.com/format-email', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    content: agentOutput,
    recipient: customerName,
    subject: reportTitle,
    sender: agentName
  })
});

const { email } = await response.json();
// Use formatted email

📝 Action Items Addressed

This MCP helps with your meeting action items:

✅ Employee Response Customization - Use validate_output_quality to test if Audrey's responses are specialized

✅ Report Generation Workflow - Use create_email_template and format_report_html to format outputs for customers

✅ MCP Integration - This entire server demonstrates MCP integration for your platform

🧪 Testing

Run the test suite:

npm test

This will test all 5 tools with example data.

📦 Package Updates

Update dependencies:

npm install @modelcontextprotocol/sdk@latest

Add Express for HTTP API:

npm install express

🐛 Troubleshooting

MCP not appearing in Claude Desktop?

• Check the path in your config is absolute
• Restart Claude Desktop completely
• Check server.js has execute permissions: chmod +x server.js

HTTP API not working?

• Make sure Express is installed: npm install express
• Check the port is available (default: 3000)
• Look for error messages in console

Tools returning errors?

• Check the input matches the expected schema
• Use the test script to validate: npm test
• Check server logs for specific error messages

🚀 Next Steps

1. Test locally - Run npm test to see it work
2. Deploy to Railway - Get a public URL for platform integration
3. Create N8N workflow - Connect to your AI Operations Platform
4. Build more tools - Add custom tools for your specific needs

📖 Additional Resources

• MCP Documentation
• N8N Documentation
• Railway Deployment Guide

👤 Author

Built by Nathan for the AI Operations Platform collaboration with Chris, David, and Charlie Butler.

📄 License

MIT