Overview
Automagik Forge provides a command-line interface for starting the web UI, managing the MCP server, and running the backend programmatically.Quick Start
Main Command
The primary command launches the Forge web interface:Options
| Option | Description | Default |
|---|---|---|
--mcp | Start in MCP server mode (basic, 6 tools) | Web UI mode |
--mcp-advanced | Start in MCP server mode (advanced, 56+ tools) | Web UI mode |
--port <port> | Specify frontend port | 3000 |
--backend-port <port> | Specify backend API port | Auto-assigned |
--host <host> | Specify host address | 127.0.0.1 |
Usage Modes
- Web UI Mode (Default)
- MCP Server Mode
Launch the full Kanban interface:Opens browser at
http://localhost:3000 with:- Visual Kanban board
- Task management interface
- Real-time execution logs
- Project settings
- GitHub integration
Environment Variables
Configure Forge behavior via environment variables:Configuration File
Forge stores configuration in your project:config.json Structure
Platform Support
Forge provides native binaries for multiple platforms:Linux
- x64 (Intel/AMD)
- ARM64
macOS
- x64 (Intel)
- ARM64 (Apple Silicon)
- Rosetta detection
Windows
- x64
- ARM64
Troubleshooting
Command not found: automagik-forge
Command not found: automagik-forge
If you installed globally but can’t run the command:
Port already in use
Port already in use
Unsupported platform error
Unsupported platform error
- Linux x64, Linux ARM64
- macOS x64 (Intel), macOS ARM64 (Apple Silicon)
- Windows x64, Windows ARM64
MCP server not responding
MCP server not responding
Programmatic Usage
While Forge is primarily a web UI, you can interact with it programmatically:Via MCP (Recommended)
Configure in your AI agent (Claude Code, Cursor, etc.):Via REST API
When Forge is running, it exposes a REST API:Next Steps
Project Commands
Manage projects and repositories
Task Commands
Create and manage tasks
Config Commands
Configuration management
MCP Tools Reference
Complete MCP tool documentation
Note: Forge is designed as a graphical web interface. The CLI primarily serves to launch the UI and provide MCP server functionality for AI agent integration.

