pm-orchestration-mcp

srdrkr/pm-orchestration-mcp

3.1

If you are the rightful owner of pm-orchestration-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.

The PM Orchestration MCP server is designed to streamline and automate project management workflows by integrating various PM tools into a unified system, reducing context switching and enabling rapid task completion.

Tools
4
Resources
0
Prompts
0

PM Orchestration MCP

Unified MCP (Model Context Protocol) server that orchestrates all PM tools through composite operations. Eliminates context switching and enables sub-5-minute task completion through intelligent tool composition.

🎯 Mission

Transform fragmented PM workflows into seamless, context-aware operations that save 60+ minutes daily through intelligent automation and aggregation.

🏗️ Architecture

User Intent → Claude → MCP Composite Tool → Internal Orchestration → Complete Result
                                            ↓
                        [PM Context Engine + Meeting Notes + Jira + n8n workflows]

🔧 Core Tools

1. get_unified_context

Search across all PM knowledge sources (230+ docs, meetings, tickets, sessions) for comprehensive context.

// Usage in Claude
"Search for information about 3PI integration architecture"

2. create_enriched_story

Create user stories/tickets with automatic context enrichment from all PM sources.

// Usage in Claude
"Create a story for implementing OAuth in the 3PI platform"

3. morning_sweep

Generate comprehensive morning brief with overnight changes, priorities, and suggested focus items.

// Usage in Claude
"Run my morning sweep"

4. process_meeting_with_context

Process meeting notes with historical context to extract actions and create enriched tickets.

// Usage in Claude
"Process this meeting transcript and extract actionable items"

🚀 Quick Start

Prerequisites

  • Node.js 18+
  • Railway account
  • AWS S3 buckets (for meeting notes and sessions)

Installation

# Clone the repository
git clone https://github.com/your-username/pm-orchestration-mcp.git
cd pm-orchestration-mcp

# Install dependencies
npm install

# Set up environment variables
cp .env.example .env
# Edit .env with your credentials

# Start the MCP server
npm start

Environment Variables

# AWS S3 Configuration
AWS_S3_MEETING_NOTES_BUCKET=your-meeting-notes-bucket
AWS_S3_SESSIONS_BUCKET=your-sessions-bucket
AWS_REGION=us-east-1
AWS_ACCESS_KEY_ID=your-access-key
AWS_SECRET_ACCESS_KEY=your-secret-key

# Railway deployment (auto-configured)
PORT=3000

🔗 Service Integrations

PM Context Engine

  • Endpoint: https://pm-context-engine-production.up.railway.app/mcp
  • Purpose: 230+ document search and retrieval
  • Status: ✅ Production ready

n8n Workflows

  • Content Generation: https://srdkr.app.n8n.cloud/webhook/pm-orchestration-trigger
  • Content Refinement: https://srdkr.app.n8n.cloud/webhook/refinement-trigger
  • Purpose: AI-powered content generation via Claude models
  • Status: ✅ Production ready

Storage

  • Meeting Notes: S3 bucket with versioning
  • Session Files: S3 bucket with GitHub sync backup
  • Format: Daily markdown files (YYYY-MM-DD.md)

📋 MCP Integration

Claude Desktop Configuration

  1. Open Claude Desktop settings
  2. Navigate to Connectors → MCP Servers
  3. Add new server:
{
  "pm-orchestration-mcp": {
    "command": "node",
    "args": ["path/to/pm-orchestration-mcp/server.js"],
    "env": {
      "AWS_S3_MEETING_NOTES_BUCKET": "your-bucket",
      "AWS_S3_SESSIONS_BUCKET": "your-bucket",
      "AWS_REGION": "us-east-1"
    }
  }
}

Claude Web/Mobile Configuration

The MCP server automatically syncs to Claude Web and Mobile once configured in Claude Desktop.

🧪 Development

Project Structure

pm-orchestration-mcp/
├── server.js              # MCP server implementation
├── package.json           # Dependencies and scripts
├── tools/
│   ├── contextTools.js    # Unified context operations
│   ├── storyTools.js      # Story creation with enrichment
│   ├── dailyTools.js      # Morning sweep and daily workflows
│   └── meetingTools.js    # Meeting processing operations
├── orchestration/
│   ├── aggregator.js      # Multi-source aggregation logic
│   └── enricher.js        # Content enrichment pipeline
├── config/
│   └── services.json      # Service endpoints and credentials
└── utils/
    ├── s3Client.js        # S3 integration
    └── sessionManager.js  # Session file management

Available Scripts

# Development with auto-reload
npm run dev

# Production start
npm start

# Test (placeholder)
npm test

Adding New Tools

  1. Create tool file in tools/ directory
  2. Implement tool class with async methods
  3. Export tool instance
  4. Register in server.js tool handlers
  5. Add tool metadata to ListToolsRequestSchema handler

📊 Performance Targets

  • Context Queries: < 2 seconds response time
  • Composite Operations: < 5 seconds response time
  • Session Persistence: 100% reliability
  • Action Extraction: 95%+ accuracy
  • Uptime: 99%+ availability

🔐 Security

  • API Keys: Stored in environment variables
  • S3 Access: IAM roles with minimal permissions
  • Service Communication: HTTPS only
  • Error Handling: No sensitive data in logs

🚀 Deployment

Railway Deployment

  1. Create Railway Project:

    railway login
railway init

  2. Connect GitHub:

    • Link repository to Railway project
    • Enable auto-deploy from main branch

  3. Set Environment Variables:

    railway variables set AWS_S3_MEETING_NOTES_BUCKET=your-bucket
railway variables set AWS_S3_SESSIONS_BUCKET=your-bucket
railway variables set AWS_REGION=us-east-1
# Add other required variables

  4. Deploy:

    git push origin main
# Railway auto-deploys

Health Check

# Test MCP server locally
echo '{"jsonrpc": "2.0", "method": "tools/list", "id": 1}' | node server.js

# Check Railway deployment
curl https://your-railway-url.railway.app/health

📈 Success Metrics

  • Time Savings: 60+ minutes/day through automation
  • Context Switching: Reduced to zero (single interface)
  • Task Completion: <5 minutes for any standard PM task
  • Accuracy: 95%+ relevance in context retrieval
  • Reliability: 99%+ uptime for critical workflows

🤝 Contributing

  1. Fork the repository
  2. Create feature branch (git checkout -b feature/amazing-feature)
  3. Commit changes (git commit -m 'Add amazing feature')
  4. Push to branch (git push origin feature/amazing-feature)
  5. Open Pull Request

📝 License

MIT License - see file for details.

🔗 Related Projects

  • PM Context Engine: Document search and retrieval
  • PM Orchestration Frontend: Web interface for content review
  • n8n Workflows: AI-powered content generation
  • Meeting Notes Pipeline: Granola → Notion → S3 automation

Built with ❤️ for Product Managers who value their time