Skip to main content
Glama

🀝 MCP Handoff Server

A Model Context Protocol (MCP) server that helps AI agents hand off work to each other with structured documentation and progress tracking.

✨ What it does

When AI agents need to pass work between each other, this server provides:

  • πŸ“ Structured handoff documents with templates

  • πŸ”„ Progress tracking from start to completion

  • πŸ“ Automatic organization of active and archived handoffs

  • πŸ” Easy searching and filtering of past work

πŸš€ Quick Start

Just run it with npx - no installation needed:

# Start in MCP mode (for MCP clients) npx -y mcp-handoff-server # Start HTTP server (for testing/direct API access) npx -y mcp-handoff-server --mode http

That's it! The server automatically creates all needed folders and templates.

πŸ“‹ Basic Usage

For MCP Clients

Add to your MCP client configuration:

{ "mcpServers": { "handoff": { "command": "npx", "args": [ "-y", "mcp-handoff-server" ] } } }

For HTTP Testing

# Start server npx -y mcp-handoff-server --mode http # Test it works curl http://localhost:3001/health

πŸ› οΈ Available Tools

The server provides these MCP tools for AI agents:

graph LR A[πŸ“ create_handoff] --> B[πŸ“– read_handoff] B --> C[πŸ”„ update_handoff] C --> D[βœ… complete_handoff] D --> E[πŸ“¦ archive_handoff] F[πŸ“‹ list_handoffs] --> B style A fill:#e1f5fe style C fill:#f3e5f5 style D fill:#e8f5e8 style E fill:#fff3e0 style F fill:#fce4ec

Tool Functions:

  • create_handoff - Start a new handoff document

  • read_handoff - Read an existing handoff

  • update_handoff - Add progress updates

  • complete_handoff - Mark work as finished

  • archive_handoff - Move completed work to archive

  • list_handoffs - Find and filter handoffs

πŸ“– Example: Creating a Handoff

# Start the server npx -y mcp-handoff-server --mode http # Create a new handoff curl -X POST http://localhost:3001/mcp \ -H "Content-Type: application/json" \ -d '{ "jsonrpc": "2.0", "id": 1, "method": "create_handoff", "params": { "type": "quick", "initialData": { "date": "2025-06-30", "time": "14:30 UTC", "currentState": { "workingOn": "Building user login", "status": "50% complete", "nextStep": "Add password validation" }, "environmentStatus": { "details": { "Server": "βœ…", "Database": "βœ…" } } } } }'

πŸ”§ Command Options

npx -y mcp-handoff-server [options] Options: --mode <mode> 'mcp' or 'http' (default: mcp) --port <port> HTTP port (default: 3001) --handoff-root <dir> Storage directory (default: ./handoff-system) --help Show help --version Show version

πŸ”„ How It Works

Simple Workflow

  1. Create a handoff when starting work

  2. Update progress as you work

  3. Complete when finished

  4. Archive for future reference

graph TD A[πŸ€– Agent Starts Work] --> B{New Work?} B -->|Yes| C[πŸ“ create_handoff] B -->|No| D[πŸ“– read_handoff] C --> E[πŸ“ Active Handoff] D --> E E --> F[πŸ”„ update_handoff] F --> G{Work Done?} G -->|No| F G -->|Yes| H[βœ… complete_handoff] H --> I[πŸ“¦ archive_handoff] I --> J[πŸ—„οΈ Archived] style C fill:#e1f5fe style F fill:#f3e5f5 style H fill:#e8f5e8 style I fill:#fff3e0

File Organization

The server automatically organizes everything in folders:

  • handoff-system/active/ - Current work

  • handoff-system/archive/ - Completed work

  • handoff-system/templates/ - Document templates

🎯 Two Types of Handoffs

πŸ“‹ Standard Handoff - For complex work with detailed context ⚑ Quick Handoff - For simple updates and brief transitions

🏷️ Status Indicators

  • βœ… Working - Everything good

  • ⚠️ Warning - Some issues but not blocked

  • ❌ Error - Problems that need fixing

πŸ› οΈ Development

Want to contribute or run locally?

# Clone and install git clone <repository-url> cd mcp-handoff-server npm install # Run in development npm run dev # Build for production npm run build

πŸ“„ License

MIT License - feel free to use this in your projects!

πŸ†˜ Need Help?


Built for seamless AI agent collaboration πŸ€–βœ¨

-
security - not tested
F
license - not found
-
quality - not tested

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/dazeb/mcp-handoff-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server