AI SummaryThis booster guides developers through implementing five specialized AI agent personas (composer, arranger, theory assistant, jam session, audio engineer) with tailored tool access and knowledge bases for music creation tasks. It benefits music software developers and AI engineers building multi-agent musical systems.
Install
Copy this and paste it into Claude Code, Cursor, or any AI assistant:
I want to set up the "Phase 6: Specialized Agents Implementation" agent in my project. Please run this command in my terminal: # Add AGENTS.md to your project root curl --retry 3 --retry-delay 2 --retry-all-errors -o AGENTS.md "https://raw.githubusercontent.com/cfogelklou/midi-mcp/main/docs/phases/06_SPECIALIZED_AGENTS.md" Then explain what the agent does and how to invoke it.
Description
Gives your AI agents the capability to play MIDI music.
Overview
Develop specialized AI agent personas with tailored tool access and knowledge bases. Each agent type has specific expertise areas, tool preferences, and interaction patterns optimized for different musical tasks.
Prerequisites
• Phases 1-5 completed and tested • Full composition and arrangement capabilities • Complete genre knowledge and music theory systems
Goals
• Implement five specialized agent types with unique capabilities • Create agent-specific tool filtering and knowledge access • Add agent personality and interaction patterns • Enable seamless switching between agent types
Day 1: Agent Architecture and Framework
Morning (3-4 hours): • Design agent persona system architecture • Implement agent switching and context management • Create agent-specific tool filtering and access control • Add agent knowledge specialization layers Code Framework: `python @mcp.tool() def activate_agent(agent_type: str) -> dict: """ Activate a specialized musical agent persona. Args: agent_type: Agent to activate (composer, arranger, theory_assistant, jam_session, audio_engineer) Returns: Agent activation status and available specialized tools """ @mcp.tool() def get_agent_capabilities(agent_type: str) -> dict: """ Get detailed capabilities and specializations of an agent type. Args: agent_type: Agent type to describe Returns: Agent's specialized tools, knowledge areas, and interaction style """ @mcp.tool() def list_active_agents() -> dict: """ List currently active agents and their contexts. Returns: Active agents, their current projects, and context information """ ` Afternoon (2-3 hours): • Create agent context persistence and memory • Add agent collaboration and handoff mechanisms • Implement agent-specific preferences and defaults • Test basic agent switching functionality HIL Test: "Ask AI to activate the composer agent and describe its capabilities"
Discussion
Health Signals
My Fox Den
Community Rating
Sign in to rate this booster