{
  "mcpServers": {
    "claude-code-mcp-enhanced": {
      "command": "npx",
      "args": [
        "github:grahama1970/claude-code-mcp-enhanced"
      ],
      "env": {
        "MCP_CLAUDE_DEBUG": "false",
        "MCP_HEARTBEAT_INTERVAL_MS": "15000",
        "MCP_EXECUTION_TIMEOUT_MS": "1800000"
      }
    }
  }
}

{
  "mcpServers": {
    "claude-code-mcp-enhanced": {
      "command": "npx",
      "args": [
        "-y",
        "@grahama1970/claude-code-mcp-enhanced@latest"
      ],
      "env": {
        "MCP_CLAUDE_DEBUG": "false",
        "MCP_HEARTBEAT_INTERVAL_MS": "15000",
        "MCP_EXECUTION_TIMEOUT_MS": "1800000"
      }
    }
  }
}

{
  "mcpServers": {
    "claude-code-mcp-enhanced": {
      "command": "node",
      "args": [
        "/path/to/claude-code-mcp-enhanced/dist/server.js"
      ],
      "env": {
        "MCP_CLAUDE_DEBUG": "false",
        "MCP_HEARTBEAT_INTERVAL_MS": "15000",
        "MCP_EXECUTION_TIMEOUT_MS": "1800000"
      }
    }
  }
}

npm install -g @anthropic-ai/claude-code

claude --dangerously-skip-permissions

{
  "mcpServers": {
    "Local MCP Server": {
      "type": "stdio",
      "command": "node",
      "args": [
        "dist/server.js"
      ],
      "env": {
        "MCP_USE_ROOMODES": "true",
        "MCP_WATCH_ROOMODES": "true",
        "MCP_CLAUDE_DEBUG": "false"
      }
    },
    "other-services": {
      // Your other MCP services here
    }
  }
}

{
  "toolName": "claude_code:health",
  "arguments": {}
}

{
  "status": "ok",
  "version": "1.12.0",
  "claudeCli": {
    "path": "claude",
    "status": "available"
  },
  "config": {
    "debugMode": true,
    "heartbeatIntervalMs": 15000,
    "executionTimeoutMs": 1800000,
    "useRooModes": true,
    "maxRetries": 3,
    "retryDelayMs": 1000
  },
  "system": {
    "platform": "linux",
    "release": "6.8.0-57-generic",
    "arch": "x64",
    "cpus": 16,
    "memory": {
      "total": "32097MB",
      "free": "12501MB"
    },
    "uptime": "240 minutes"
  },
  "timestamp": "2025-05-15T18:30:00.000Z"
}

{
  "toolName": "claude_code:convert_task_markdown",
  "arguments": {
    "markdownPath": "/home/user/tasks/validation.md",
    "outputPath": "/home/user/tasks/validation.json"
  }
}

{
  "toolName": "claude_code:claude_code",
  "arguments": {
    "prompt": "Your work folder is /path/to/project\n\nRefactor the function foo in main.py to be async.",
    "workFolder": "/path/to/project"
  }
}

{
  "toolName": "claude_code:claude_code",
  "arguments": {
    "prompt": "Your work folder is /path/to/project\n\nOrchestrate the implementation of a new API endpoint with the following subtasks:\n1. Create database models\n2. Implement API route handlers\n3. Write unit tests\n4. Document the API",
    "workFolder": "/path/to/project"
  }
}

{
  "toolName": "claude_code:claude_code",
  "arguments": {
    "prompt": "Your work folder is /path/to/project\n\nCreate database models for the new API endpoint as specified in the requirements.",
    "workFolder": "/path/to/project",
    "parentTaskId": "task-123",
    "returnMode": "summary",
    "taskDescription": "Database model creation for API endpoint"
  }
}

{
  "toolName": "claude_code:claude_code",
  "arguments": {
    "prompt": "Your work folder is /path/to/project\n\nCreate unit tests for the user authentication module.",
    "workFolder": "/path/to/project",
    "mode": "coder"
  }
}

graph TD
    A["👤 User"] -->|"Create tasks.md"| B["📝 Multi-Task Markdown"]
    A -->|"Prompt Claude"| C["🤖 Claude Desktop"]
    C -->|"Use convert_task_markdown"| D["🔄 Task Converter MCP"]
    D -->|"Validate Format"| E{"Format Valid?"}
    E -->|"No"| F["📑 Error + Fix Instructions"]
    F -->|"Return to User"| A
    E -->|"Yes"| G["📋 MCP Task List"]
    G -->|"Execute Task"| H1["⚡ Claude Task #1"]
    H1 -->|"Complete"| I1["Next Task"]
    I1 -->|"Execute Task"| H2["⚡ Claude Task #2"]
    H2 -->|"Complete"| I2["Next Task"]
    I2 -->|"Execute Task"| H3["⚡ Claude Task #3"]
    H3 -->|"Complete"| I3["More Tasks"]
    I3 -->|"Execute Task"| HN["⚡ Claude Task #N"]
    HN -->|"Complete"| IN["🎉 All Tasks Completed!"]
    
    style A fill:#4A90E2,stroke:#fff,stroke-width:2px,color:#fff
    style C fill:#7C4DFF,stroke:#fff,stroke-width:2px,color:#fff
    style D fill:#00BCD4,stroke:#fff,stroke-width:2px,color:#fff
    style F fill:#FF5252,stroke:#fff,stroke-width:2px,color:#fff
    style G fill:#4CAF50,stroke:#fff,stroke-width:2px,color:#fff
    style H1 fill:#FFC107,stroke:#fff,stroke-width:2px,color:#fff
    style H2 fill:#FFC107,stroke:#fff,stroke-width:2px,color:#fff
    style H3 fill:#FFC107,stroke:#fff,stroke-width:2px,color:#fff
    style HN fill:#FFC107,stroke:#fff,stroke-width:2px,color:#fff
    style IN fill:#4CAF50,stroke:#fff,stroke-width:2px,color:#fff

{
  "tool": "convert_task_markdown",
  "arguments": {
    "markdownPath": "/path/to/tasks.md",
    "outputPath": "/path/to/output.json" // optional
  }
}

{
  "tasksCount": 5,
  "outputPath": "/path/to/output.json",
  "tasks": [
    {
      "tool": "claude_code",
      "arguments": {
        "command": "cd /project && source .venv/bin/activate\n\nTASK TYPE: Validation...",
        "dangerously_skip_permissions": true,
        "timeout_ms": 300000
      }
    }
    // ... more tasks
  ]
}

# Task 001: Task Title

## Objective
Clear description of what needs to be accomplished.

## Requirements
1. [ ] First requirement
2. [ ] Second requirement

## Tasks

### Module or Component Name
- [ ] Validate `path/to/file.py`
   - [ ] Step 1
   - [ ] Step 2
   - [ ] Step 3

# Task 001: API Endpoint Validation

## Objective
Validate all API endpoints work with real database connections.

## Requirements
1. [ ] All endpoints must use real database
2. [ ] No mock data in validation

## Core API Tasks
- [ ] Validate `api/users.py`
   - [ ] Change directory to project and activate .venv
   - [ ] Test user creation endpoint
   - [ ] Test user retrieval endpoint
   - [ ] Verify JSON responses

{
  "tool": "convert_task_markdown",
  "arguments": {
    "markdownPath": "/project/tasks/api_validation.md"
  }
}

# Task 001: Setup Development Environment

## Objective
Initialize the development environment with all dependencies.

## Requirements
1. [ ] Python 3.11+ installed
2. [ ] Virtual environment created

## Tasks
- [ ] Validate `setup.py`
   - [ ] Change to project directory
   - [ ] Create virtual environment
   - [ ] Install dependencies

Use convert_task_markdown to process /home/user/project_tasks.md

[
  {
    "tool": "claude_code",
    "arguments": {
      "prompt": "cd /home/user/project && python -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt",
      "workFolder": "/home/user/project"
    }
  }
]

{
  "status": "error",
  "error": "Markdown format validation failed",
  "details": "Markdown format validation failed:\n  - Missing required title. Format: '# Task NNN: Title'\n  - Missing or empty 'Requirements' section. Format: '## Requirements\\n1. [ ] Requirement'\n  - No validation tasks found. Format: '- [ ] Validate `module.py`' with indented steps\n\nRequired markdown format:\n# Task NNN: Title\n## Objective\nClear description\n## Requirements\n1. [ ] First requirement\n## Task Section\n- [ ] Validate `file.py`\n   - [ ] Step 1\n   - [ ] Step 2",
  "helpUrl": "https://github.com/grahama1970/claude-code-mcp-enhanced/blob/main/README.md#markdown-task-file-format"
}

graph TB
    User("👨‍🍳 User")
    Claude("🤖 Claude (Parent)")
    Code1("🧁 Claude Code")
    Code2("🧁 Claude Code")
    
    User-->|"Make chocolate cake"| Claude
    Claude-->|"Task 1: Find recipe"| Code1
    Code1-->|"Result: Recipe found"| Claude
    Claude-->|"Task 2: Convert measurements"| Code2
    Code2-->|"Result: Measurements converted"| Claude
    Claude-->|"Complete recipe + instructions"| User

{
  "toolName": "claude_code:claude_code",
  "arguments": {
    "prompt": "Search for a classic chocolate cake recipe. Find one with good reviews.",
    "parentTaskId": "cake-recipe-123",
    "returnMode": "summary",
    "taskDescription": "Find Chocolate Cake Recipe"
  }
}

{
  "toolName": "claude_code:claude_code",
  "arguments": {
    "prompt": "Convert the measurements in this recipe from cups to grams:\n\n- 2 cups flour\n- 1.5 cups sugar\n- 3/4 cup cocoa powder",
    "parentTaskId": "cake-recipe-123",
    "returnMode": "summary",
    "taskDescription": "Convert Recipe Measurements"
  }
}

You: I need to refactor this codebase. It's quite complex.

Claude Desktop: I'll help you with that. Let me break this down into smaller tasks for Claude Code to handle:

1. First, I'll have Claude Code analyze the codebase structure
2. Then, I'll have it identify problematic patterns
3. Finally, I'll ask it to generate a refactoring plan

[Claude Desktop sends a request to the claude_code tool with parentTaskId="task1" and returnMode="summary"]

[Claude Code analyzes the codebase and returns a summary with the BOOMERANG_RESULT marker]

Claude Desktop: Based on Claude Code's analysis, here are the key issues found:
- Duplicate code in modules X and Y
- Poor separation of concerns in module Z
- Inconsistent naming conventions

Now I'll ask Claude Code to suggest specific refactorings...

# Project Task List

## Parent Task: API Optimization Project
- [ ] Optimize API performance for high-traffic endpoints
  - [ ] Analyze current API performance and identify bottlenecks
  - [ ] Implement database query optimization for user endpoints
  - [ ] Add Redis caching for frequently accessed data
  - [ ] Set up performance monitoring

## Assumptions and Decisions
- [2025-05-15] Assumption: Redis is available in the infrastructure
- [2025-05-15] Decision: Focus on user endpoints first (Rationale: Highest traffic area)

## Relevant Files
- `src/controllers/userController.js`: User API endpoints
- `src/services/userService.js`: Business logic for user operations

## Improvement Notes
- Pattern identified: N+1 query issue in user listing endpoint
- Automation opportunity: Add caching automatically for all get-by-id endpoints

You: Please help me execute the task list in tasks.md, starting with the first subtask.

Claude: I'll help you work through your task list systematically. Let me first check the current task list to identify the next task to work on.

[Claude uses claude_code to read the task list]

I see the first subtask is "Analyze current API performance and identify bottlenecks". I'll execute this task now using Claude Code.

[Claude sends the following request to claude_code]:

{
  "toolName": "claude_code",
  "arguments": {
    "prompt": "Your work folder is /path/to/project\n\nTASK TYPE: Analysis\nTASK ID: api-perf-analysis\nCURRENT SUBTASK: Analyze current API performance and identify bottlenecks\n\nCONTEXT:\n- Parent task goal: Optimize API performance for high-traffic endpoints\n- This is the first step in our optimization process\n- Focus on user endpoints as noted in assumptions\n\nINSTRUCTIONS:\n1. Analyze the current API implementation in src/controllers/userController.js and src/services/userService.js\n2. Run performance tests on the user endpoints\n3. Identify specific bottlenecks and performance issues\n4. Document findings in a clear, structured format\n5. Update task list file after completion\n\nAfter completion, provide summary in this format:\n\nCOMPLETION SUMMARY:\n- What was done:\n- Results:\n- Files analyzed:\n- Issues identified:\n- Recommendations:\n- Next subtask in list:",
    "workFolder": "/path/to/project"
  }
}

[Claude Code executes the analysis task and returns results]

Great! Claude Code has completed the analysis. Here's what was found:

1. Main performance bottlenecks identified:
   - N+1 query problem in the user listing endpoint
   - Missing indexes on frequently queried fields
   - No caching for repetitive data lookups

2. Recommendations:
   - Add eager loading for user relationships
   - Create database indexes for user_id and email fields
   - Implement Redis caching with a 5-minute TTL

Let me update the task list to mark this task as complete and proceed to the next one.

[Claude uses claude_code to update the task list]:

{
  "toolName": "claude_code",
  "arguments": {
    "prompt": "Your work folder is /path/to/project\n\nTASK TYPE: Task List Update\n\n1. Read the current task list in tasks.md\n2. Mark the 'Analyze current API performance and identify bottlenecks' subtask as [x]\n3. Add new findings to the Improvement Notes section\n4. Add any new relevant files identified during analysis\n5. Write updated task list\n6. Return the updated task list",
    "workFolder": "/path/to/project"
  }
}

[Claude Code updates the task list and marks the first subtask complete]

I've updated the task list. The first subtask is now complete, and I've added the detailed findings to the Improvement Notes section. The next subtask is "Implement database query optimization for user endpoints".

Would you like me to proceed with this next subtask now?

You: Yes, please proceed with the next subtask.

Claude: I'll now execute the next subtask: "Implement database query optimization for user endpoints". This will involve fixing the N+1 query problem identified in the analysis and adding appropriate database indexes.

[Claude sends the following request to claude_code]:

{
  "toolName": "claude_code",
  "arguments": {
    "prompt": "Your work folder is /path/to/project\n\nTASK TYPE: Code Implementation\nTASK ID: db-query-optimization\nCURRENT SUBTASK: Implement database query optimization for user endpoints\n\nCONTEXT:\n- Parent task goal: Optimize API performance for high-traffic endpoints\n- Previous subtask identified N+1 query issues and missing indexes\n- Need to implement eager loading and proper indexes\n\nINSTRUCTIONS:\n1. Modify src/controllers/userController.js to implement eager loading for related data\n2. Add appropriate database indexes to user-related tables\n3. Refactor any inefficient database queries in userService.js\n4. Ensure changes maintain existing functionality\n5. Run tests to verify performance improvements\n6. Update task list file after completion\n\nAfter completion, provide summary in this format:\n\nCOMPLETION SUMMARY:\n- What was done:\n- Results:\n- Files modified:\n- Performance improvements:\n- Next subtask in list:",
    "workFolder": "/path/to/project"
  }
}

[Claude Code implements the optimizations and returns results]

Excellent! The database query optimizations have been successfully implemented. Here's a summary:

1. Changes made:
   - Added eager loading in userController.js for user relationships
   - Created new database indexes for user_id and email fields
   - Refactored list query to use a single efficient JOIN statement
   - Added pagination to prevent large result sets

2. Performance results:
   - User listing endpoint response time reduced by 68%
   - Database query count reduced from 25+ to 3 for typical requests

Let me update the task list again to reflect this progress.

[Claude uses claude_code to update the task list again]:

{
  "toolName": "claude_code",
  "arguments": {
    "prompt": "Your work folder is /path/to/project\n\nTASK TYPE: Task List Update\n\n1. Read the current task list in tasks.md\n2. Mark the 'Implement database query optimization for user endpoints' subtask as [x]\n3. Add new files modified to the Relevant Files section\n4. Update Improvement Notes with performance metrics\n5. Write updated task list\n6. Return the updated task list",
    "workFolder": "/path/to/project"
  }
}

[Claude Code updates the task list and marks the second subtask complete]

I've updated the task list again. Two subtasks are now complete, and the next one is "Add Redis caching for frequently accessed data". Would you like me to continue with this subtask?

graph TB
    User("👨‍💻 User")
    ClaudeCode("🤖 Claude Code\nOrchestrator")
    ClaudeCodeSubtask1("⚙️ Claude Code\nSubtask 1")
    ClaudeCodeSubtask2("⚙️ Claude Code\nSubtask 2")
    
    User-->|"Complex project request"| ClaudeCode
    ClaudeCode-->|"1. Plans tasks"| ClaudeCode
    ClaudeCode-->|"2. Executes subtask 1"| ClaudeCodeSubtask1
    ClaudeCodeSubtask1-->|"3. Returns result"| ClaudeCode
    ClaudeCode-->|"4. Executes subtask 2"| ClaudeCodeSubtask2
    ClaudeCodeSubtask2-->|"5. Returns result"| ClaudeCode
    ClaudeCode-->|"6. Final solution"| User