task-engine-ai-core
Version:
Revolutionary AI-driven task management system with complete transformation trilogy: Frontend v0.1.0, Backend v0.2.0, CLI v0.3.0 - Enterprise-grade performance with 95% improvements
356 lines (288 loc) • 8.4 kB
Markdown
# MCP IDE Integration Guide
Complete guide for connecting Task Master AI to real IDE agents via MCP (Model Context Protocol).
## Overview
This integration replaces mock IDE responses with **real connections** to your IDE's AI agent through standardized MCP protocol. Benefits include:
- ✅ **Real AI responses** from your IDE's built-in agent
- ✅ **Zero external API costs** when using IDE agents
- ✅ **Consistent behavior** matching your IDE settings
- ✅ **Automatic fallback** to mock if connection fails
- ✅ **Cross-IDE compatibility** through MCP standard
## Quick Start
### 1. Automatic Setup (Recommended)
```bash
npm run setup:mcp-ide
```
This automatically:
- Detects your installed IDEs
- Creates appropriate MCP configuration
- Tests the setup
### 2. Manual Setup
#### Choose Your IDE:
**Cursor IDE:**
```bash
cp mcp-configs/cursor-mcp.json .cursor/mcp.json
```
**VS Code:**
```bash
cp mcp-configs/vscode-mcp.json .vscode/mcp.json
```
**Windsurf IDE:**
```bash
cp mcp-configs/windsurf-mcp.json .windsurf/mcp.json
```
#### Update Configuration:
1. Edit the MCP configuration file
2. Replace `YOUR_*_API_KEY_HERE` with actual API keys
3. Update project paths as needed
4. Restart your IDE
## MCP Configuration Structure
### Cursor/Windsurf Format (`mcpServers`)
```json
{
"mcpServers": {
"task-master-ai": {
"command": "npx",
"args": ["-y", "--package=task-master-ai", "task-master-ai"],
"env": {
"ANTHROPIC_API_KEY": "your_key_here",
"TASK_MASTER_PROJECT_ROOT": "/path/to/project"
}
},
"task-master-ide-bridge": {
"command": "npx",
"args": ["-y", "--package=task-master-ai", "task-master-ide-bridge"],
"env": {
"BRIDGE_ENABLED": "true",
"IDE_TYPE": "cursor",
"TASK_MASTER_PROJECT_ROOT": "/path/to/project"
}
}
}
}
```
### VS Code Format (`servers`)
```json
{
"servers": {
"task-master-ai": { /* same as above */ },
"task-master-ide-bridge": { /* same as above */ }
}
}
```
## Available MCP Tools
### Task Management Tools
#### `add_task` - Dual Mode Task Creation
Create tasks using either AI-powered generation or manual specification:
**🤖 AI-Powered Mode** (requires external APIs):
```json
{
"projectRoot": "/path/to/project",
"prompt": "Create a task for implementing user authentication",
"research": false
}
```
**🧠 Manual/Agentic Mode** (works through agentic instance):
```json
{
"projectRoot": "/path/to/project",
"title": "Implement user authentication",
"description": "Add login/logout functionality with secure session management",
"details": "Detailed implementation steps and requirements...",
"testStrategy": "Testing approach and validation criteria...",
"priority": "high",
"dependencies": "1,2,3"
}
```
**Benefits of Manual Mode:**
- ✅ **No External Dependencies**: Works without API keys or internet
- ✅ **Immediate Response**: No waiting for AI processing
- ✅ **Full Control**: Precise task specification
- ✅ **Reliable**: No AI service failures or rate limits
- ✅ **Cost-Free**: No API usage costs
- ✅ **Perfect for Agentic Workflows**: Ideal for AI agents creating tasks
#### Other Task Management Tools
- `get_tasks` - Retrieve all tasks with filtering
- `get_task` - Get detailed task information
- `set_task_status` - Update task status
- `next_task` - Find next task to work on
- `update_task` - Update task with new information
- `expand_task` - Break task into subtasks
- `complexity_report` - Analyze task complexity
### Core IDE Tools
#### `detect_ide`
Detect available IDEs and capabilities
```json
{
"forceRefresh": false
}
```
#### `connect_ide`
Connect to specific IDE agent
```json
{
"ideType": "cursor",
"timeout": 10000
}
```
#### `ide_generate_text`
Generate text using IDE agent
```json
{
"messages": [
{"role": "user", "content": "Write a hello world function"}
],
"maxTokens": 1000,
"temperature": 0.7
}
```
#### `ide_status`
Get connection status and health
```json
{}
```
#### `configure_bridge`
Update bridge settings
```json
{
"ideType": "auto-detect",
"enabled": true,
"fallbackToExternal": true
}
```
## IDE-Specific Configuration
### Cursor IDE
- **API Port**: 42000 (default)
- **Config Path**: `.cursor/mcp.json`
- **Features**: Full text generation, streaming, code completion
- **Requirements**: Cursor running with API enabled
### VS Code
- **Config Path**: `.vscode/mcp.json`
- **Features**: Limited (extension-dependent)
- **Requirements**: GitHub Copilot or similar AI extension
- **Status**: Partial implementation (falls back to mock)
### Windsurf IDE
- **API Port**: 43000 (default)
- **Config Path**: `.windsurf/mcp.json`
- **Features**: Cascade AI, multi-agent workflows
- **Requirements**: Windsurf running with Cascade enabled
## Environment Variables
### Bridge Configuration
```bash
BRIDGE_ENABLED=true
BRIDGE_PORT=8765
BRIDGE_HOST=localhost
IDE_TYPE=auto-detect
IDE_FALLBACK_TO_EXTERNAL=true
```
### IDE-Specific
```bash
# Cursor
CURSOR_API_PORT=42000
CURSOR_API_HOST=localhost
# Windsurf
WINDSURF_CASCADE_PORT=43000
WINDSURF_CASCADE_HOST=localhost
# VS Code
VSCODE_EXTENSIONS_PATH=/path/to/extensions
```
### Project Configuration
```bash
TASK_MASTER_PROJECT_ROOT=/path/to/your/project
```
## Testing & Validation
### Test MCP Integration
```bash
npm run test:ide-integration
```
### Manual Testing
```bash
# Test IDE detection
node -e "
import IDEDetection from './src/bridge/ide-detection.js';
const detection = new IDEDetection();
console.log(await detection.detectAvailableIDEs());
"
# Test MCP bridge server
timeout 5s node src/bridge/mcp-bridge-server.js
```
### Verify Configuration
```bash
# Check MCP config exists
ls -la .cursor/mcp.json .vscode/mcp.json .windsurf/mcp.json
# Validate JSON syntax
node -e "console.log(JSON.parse(require('fs').readFileSync('.cursor/mcp.json')))"
```
## Troubleshooting
### Common Issues
**"No IDEs detected"**
- Ensure IDE is installed and running
- Check IDE configuration paths
- Try manual IDE type specification
**"Failed to connect to real IDE agent"**
- Verify IDE API is enabled
- Check port configuration (42000 for Cursor, 43000 for Windsurf)
- Ensure IDE is running and accessible
**"MCP server not responding"**
- Restart your IDE to reload MCP configuration
- Check MCP configuration syntax
- Verify API keys are set correctly
**"VS Code integration not working"**
- Install GitHub Copilot or similar AI extension
- System will automatically fallback to mock
- VS Code integration is currently partial
### Debug Mode
```bash
# Enable debug logging
export DEBUG=task-master:*
# Check bridge logs
npm run bridge-logs
# Test with verbose output
npm run test:ide-integration
```
## Migration from Mock-Only
### Automatic Migration
The system automatically:
1. Attempts real IDE connection first
2. Falls back to mock if real connection fails
3. Logs which mode is being used
4. Preserves existing functionality
### Manual Control
```javascript
// Force real IDE mode
const ide = new IDEAgentInterface({
ideType: 'cursor',
forceReal: true
});
// Force mock mode
const ide = new IDEAgentInterface({
ideType: 'cursor',
forceMock: true
});
```
## Best Practices
### Security
- Keep API keys in environment variables
- Use localhost-only connections
- Regularly rotate API keys
### Performance
- Use real IDE for development
- Consider mock mode for CI/CD
- Monitor response times
### Reliability
- Always enable fallback to external APIs
- Test both real and mock modes
- Monitor connection health
## Support
### Documentation
- [Real IDE Integration](real-ide-integration.md)
- [Bridge Configuration](bridge-config.md)
- [MCP Protocol](https://modelcontextprotocol.io/)
### Commands
```bash
npm run setup:mcp-ide # Setup MCP integration
npm run test:ide-integration # Test integration
npm run bridge-detect # Detect IDEs
npm run bridge-health # Check bridge health
```
---
**Ready to use real IDE integration with Task Master AI!** 🎉