Skip to main content
Glama

BMAD MCP Server

by Dali1789
GitHub
Python
MIT License
OverviewInspectNewEndpointsSchemaRelated ServersReviewsScore
Need Help?View Source CodeReport Issue

BMAD MCP Server 🚀

A comprehensive Model Context Protocol (MCP) server implementing the BMAD (Business Modeling and Development) methodology. Provides intelligent task management, multi-agent workflows, and cross-IDE project management through the MCP protocol.

✨ Features

🤖 6 Specialized AI Agents

  • 📊 Analyst: Business analysis, market research, requirement gathering
  • 🏗️ Architect: System design, architecture planning, tech stack selection
  • 💻 Developer: Code implementation, debugging, technical development
  • 📋 Project Manager: Task coordination, timeline management, resource planning
  • 🔍 QA: Quality assurance, testing strategies, code review
  • 🔍 Coder Agent: Advanced semantic code analysis and editing capabilities ⭐ NEW!

📋 Advanced Task Management

  • Real-time Progress Tracking: Live updates and notifications
  • Intelligent Scheduling: Auto-allocation with capacity management
  • Follow-up Task Generation: Automatic workflow progression
  • Notion Integration: Bi-directional sync with Notion databases
  • TodoWrite Bridge: Seamless Claude integration

⏱️ Time & Cost Tracking ⭐ NEW!

  • Precise Time Tracking: Exact time spent on each project with session management
  • AI Cost Calculation: Automatic calculation of AI model costs per project
  • Project Billing: Comprehensive billing reports for client invoicing
  • Multi-format Export: JSON, CSV, and invoice-style billing reports
  • Cost Optimization: Track and optimize AI model usage across projects
  • Session Management: Auto-end stale sessions and track work patterns

🎨 Template-System & Standardisierte Projektstrukturen ⭐ NEW!

  • 6 Projekt-Templates: standard, web-app, api, mobile, data-science, infrastructure
  • Automatische Struktur-Erstellung: Einheitliche .bmad-core/ Verzeichnisse
  • Auto-Discovery: Erkennt automatisch neue BMAD-Projekte
  • Migration-Tools: Migriert bestehende Projekte auf BMAD v2.0 Standard
  • Zero-Setup: Neue Projekte sind sofort produktiv mit kompletter Konfiguration

🔄 Enhanced Features

  • BMAD-METHOD Workflow System: Complete implementation with intelligent orchestration ⭐ NEW!
  • Quality Gates (@qa commands): 6 comprehensive quality assurance commands ⭐ NEW!
  • Advanced Semantic Code Analysis: Professional code intelligence via Coder Agent ⭐ NEW!
  • Time-based Monitoring: Scheduled reminders and progress checks
  • Work Day Simulation: Demo modes and realistic progression testing
  • Live Console Output: Beautiful formatted status displays
  • Project Context Integration: Multi-project support with global registry
  • Performance Metrics: Detailed tracking and reporting

🌐 Universal IDE Access

Compatible with any IDE supporting MCP:

  • Claude Code ✅
  • VS Code ✅
  • Cursor ✅
  • Any MCP-compatible IDE ✅

🚀 Quick Start

Prerequisites

  • Python 3.8+
  • OpenRouter API Key (for AI model routing)
  • Notion API Token (optional, for database sync)

Installation

# 1. Clone the repository git clone https://github.com/yourusername/bmad-mcp-server.git cd bmad-mcp-server # 2. Install dependencies pip install -r requirements.txt # 3. Set up environment variables cp .env.example .env # Edit .env with your API keys

Configuration

Add to your IDE's MCP configuration:

Claude Code (claude_desktop_config.json)
{ "mcpServers": { "bmad": { "command": "python", "args": ["-m", "src.bmad_mcp.server"], "cwd": "/path/to/bmad-mcp-server", "env": { "PYTHONPATH": "/path/to/bmad-mcp-server", "OPENROUTER_API_KEY": "your_openrouter_api_key", "NOTION_TOKEN": "your_notion_token" } } } }
VS Code / Cursor
{ "mcp.servers": { "bmad": { "command": "python", "args": ["-m", "src.bmad_mcp.server"], "cwd": "/path/to/bmad-mcp-server", "env": { "PYTHONPATH": "/path/to/bmad-mcp-server", "OPENROUTER_API_KEY": "your_openrouter_api_key" } } } }

🛠️ Available MCP Tools

🤖 Agent Management

ToolDescriptionExample
bmad_list_agentsList all available agentsShows 5 specialized agents
bmad_activate_agentSwitch to specific agentagent: "dev"
bmad_get_agent_helpGet agent-specific guidanceContext-aware help

📋 Task Management

ToolDescriptionExample
bmad_get_task_summaryComprehensive task overviewProgress, metrics, status
bmad_create_taskCreate new task with auto-schedulingtask_id, name, hours
bmad_update_task_progressUpdate progress with real-time synctask_id, hours_completed
bmad_get_today_tasksToday's scheduled tasksDaily workload view
bmad_get_agent_tasksAgent-specific task listFilter by agent

⏱️ Time & Cost Tracking ⭐ NEW!

ToolDescriptionExample
bmad_start_timerStart time tracking for a tasktask_id, agent, session_type
bmad_stop_timerStop timer and calculate coststask_id, ai_model, tokens
bmad_get_active_timersList all currently running timersActive sessions overview
bmad_get_task_time_summaryTime tracking summary for taskHours, cost, sessions
bmad_get_daily_time_reportDaily time tracking reportProject breakdown, hours
bmad_get_project_billingGenerate project billing reportJSON, CSV, invoice formats
bmad_auto_end_stale_sessionsEnd sessions running too longCleanup stale timers
bmad_update_model_costsUpdate AI model pricingConfigure cost per token
bmad_get_model_costsGet current model costsView pricing configuration

⚡ Enhanced Features

ToolDescriptionExample
bmad_start_realtime_modeEnable live task monitoringBackground updates
bmad_start_work_sessionTrack work session for taskTime tracking
bmad_simulate_work_dayDemo realistic work progressionTesting & demos
bmad_get_project_statusComprehensive project overviewMulti-project support
bmad_sync_notion_tasksSync with Notion databasesBi-directional sync

🔧 Project Management

ToolDescriptionExample
bmad_detect_projectScan for BMAD configurationAuto-discovery
bmad_register_projectAdd project to global registryCross-IDE access
bmad_execute_taskRun BMAD methodology tasksTemplate-based execution
bmad_create_documentGenerate documents from templatesAutomated documentation
bmad_run_checklistQuality assurance checklistsQA workflows

🚀 BMAD-METHOD Workflow System ⭐ NEW!

ToolDescriptionExample
bmad_workflow_start_projectStart BMAD-METHOD project workflowFull/planning/development modes
bmad_workflow_advanceAdvance workflow to next stateProject/story state transitions
bmad_workflow_start_storyCreate story in development cycleStory creation & planning
bmad_workflow_run_qaExecute quality gate (@qa commands)*risk, *design, *trace, *nfr, *review, *gate
bmad_workflow_execute_commandRoute agent commands intelligentlyContext-aware agent routing
bmad_workflow_get_statusGet comprehensive workflow statusReal-time progress monitoring
bmad_workflow_generate_reportGenerate detailed workflow reportsAnalytics & recommendations

🔍 Semantic Code Analysis ⭐ NEW!

ToolDescriptionExample
bmad_coder_activate_projectActivate project for analysisSemantic code intelligence
bmad_coder_find_symbolFind code symbols semanticallyFunctions, classes, variables
bmad_coder_get_symbols_overviewGet file symbol overviewCode structure analysis
bmad_coder_find_referencing_symbolsFind symbol referencesCross-reference tracking
bmad_coder_insert_after_symbolInsert code after symbolPrecise code insertion
bmad_coder_replace_symbol_bodyReplace symbol implementationCode modification
bmad_coder_execute_shell_commandExecute shell commandsTesting, building, automation
bmad_coder_search_for_patternAdvanced pattern searchIntelligent code search
bmad_coder_write_memoryStore project knowledgePersistent insights
bmad_coder_read_memoryLoad stored knowledgeAccess project memories

🎨 Template-System ⭐ NEW!

ToolDescriptionExample
bmad_create_projectCreate project with standardized structurepath, template
bmad_list_project_templatesShow all available templates6 templates available
bmad_get_project_template_infoDetailed template informationFeatures, structure
bmad_migrate_project_to_standardMigrate existing projectAuto-backup, structure

📊 Usage Examples

Basic Task Management

# List available agents bmad_list_agents() # Activate developer agent bmad_activate_agent(agent="dev") # Create a new task bmad_create_task( task_id="feature-implementation", name="Implement user authentication", allocated_hours=8.0, agent="dev" ) # Update progress bmad_update_task_progress( task_id="feature-implementation", hours_completed=2.5 ) # Get daily overview bmad_get_today_tasks()

Real-time Monitoring

# Start live monitoring bmad_start_realtime_mode() # Begin work session bmad_start_work_session(task_id="feature-implementation") # Work on task... # End session with automatic progress logging bmad_end_work_session( task_id="feature-implementation", hours_worked=2.0 ) # Get comprehensive status bmad_get_realtime_status()

Time & Cost Tracking ⭐ NEW!

# Start time tracking for a task bmad_start_timer( task_id="feature-implementation", agent="dev", session_type="development", description="Implementing user authentication system" ) # Stop timer with AI cost calculation bmad_stop_timer( task_id="feature-implementation", ai_model_used="claude-sonnet-4", tokens_input=1500, tokens_output=800, mark_completed=False ) # Get task time summary bmad_get_task_time_summary(task_id="feature-implementation") # Generate project billing report bmad_get_project_billing( project_id="my-project-id", start_date="2025-01-01", end_date="2025-01-31", export_format="invoice" # json, csv, or invoice ) # Get daily tracking report bmad_get_daily_time_report(date="2025-01-20") # Auto-end stale sessions (running >8 hours) bmad_auto_end_stale_sessions(max_hours=8)

Project Context

# Detect BMAD project bmad_detect_project(path="./my-project") # Register in global registry bmad_register_project( project_path="./my-project", project_name="My Awesome Project" ) # Get project overview bmad_get_project_status()

Template-System Usage ⭐ NEW!

# List available templates bmad_list_project_templates() # Get template details bmad_get_project_template_info(template_name="web-app") # Create new project with template bmad_create_project( project_path="./my-web-app", template="web-app", name="My Web Application", description="Modern React-based web application" ) # Migrate existing project bmad_migrate_project_to_standard( project_path="./legacy-project", backup=True )

Available Templates

  • standard: Basic BMAD project with full structure
  • web-app: Frontend/Backend with React/Vue/Angular support
  • api: REST/GraphQL APIs with OpenAPI documentation
  • mobile: React Native/Flutter cross-platform apps
  • data-science: ML/Jupyter with notebooks and data pipelines
  • infrastructure: Docker/Terraform/Kubernetes deployments

Simulation & Testing

# Simulate full work day bmad_simulate_work_day(speed_factor=10.0) # Test specific agent workflow bmad_simulate_agent_workday(agent="qa", hours=6.0) # Simulate crisis scenarios bmad_simulate_crisis_scenario(crisis_type="blocked_task")

Advanced Time Tracking Workflows ⭐ NEW!

# Start comprehensive work session bmad_start_timer( task_id="user-auth-system", agent="dev", session_type="development", description="Implementing OAuth2 integration" ) # Work on task with AI assistance # ... development work with AI model usage ... # Stop timer with detailed AI cost tracking bmad_stop_timer( task_id="user-auth-system", ai_model_used="claude-sonnet-4", tokens_input=2500, tokens_output=1200, mark_completed=True ) # Generate comprehensive project billing billing_report = bmad_get_project_billing( project_id="client-project-2025", start_date="2025-01-01", end_date="2025-01-31", export_format="invoice" ) # Monitor daily productivity daily_report = bmad_get_daily_time_report("2025-01-20") print(f"Today: {daily_report['total_hours']:.2f}h, ${daily_report['total_cost_usd']:.2f}") # Automatic session management bmad_auto_end_stale_sessions(max_hours=6) # End sessions > 6 hours

🏗️ Architecture

bmad-mcp-server/ ├── src/ │ └── bmad_mcp/ │ ├── core/ # Core functionality │ │ ├── task_tracker.py # Advanced task management │ │ ├── time_cost_tracker.py # Time & cost tracking ⭐ NEW! │ │ ├── console_formatter.py # Live output formatting │ │ ├── realtime_updater.py # Real-time monitoring │ │ ├── time_monitor.py # Scheduled monitoring │ │ ├── simulator.py # Demo & testing │ │ ├── notion_sync.py # Notion integration │ │ └── global_registry.py # Cross-IDE projects │ ├── agents/ # Agent definitions │ │ ├── analyst.py # Business analysis │ │ ├── architect.py # System design │ │ ├── developer.py # Code implementation │ │ ├── project_manager.py # Project coordination │ │ ├── qa.py # Quality assurance │ │ └── coder.py # Advanced semantic code analysis and editing │ ├── workflows/ # BMAD-METHOD workflow system │ │ ├── workflow_engine.py # Central workflow orchestration │ │ ├── orchestrator_agent.py # Project/Story lifecycle management │ │ ├── quality_gates.py # Quality assurance (@qa commands) │ │ └── workflow_states.py # State machine definitions │ ├── tools/ # MCP tool implementations │ ├── routing/ # OpenRouter integration │ └── server.py # MCP server ├── config/ # Configuration templates ├── docs/ # Documentation ├── examples/ # Usage examples └── tests/ # Test suite

🔧 Configuration

Environment Variables

# Required OPENROUTER_API_KEY=your_openrouter_api_key_here # Optional NOTION_TOKEN=your_notion_integration_token BMAD_MAX_DAILY_HOURS=10 BMAD_DEFAULT_AGENT=dev BMAD_LOG_LEVEL=INFO

Agent Configuration

Each agent can be customized via configuration files:

# config/bmad-global-config.yaml agents: dev: model: "anthropic/claude-3.5-sonnet" temperature: 0.1 max_tokens: 4000 architect: model: "anthropic/claude-3-opus" temperature: 0.3 max_tokens: 8000

🐳 Docker Deployment

# Build and run with Docker Compose docker-compose up -d # Environment variables via .env file cp .env.example .env # Edit .env file with your API keys docker-compose up -d

🧪 Testing

# Run test suite python -m pytest tests/ # Run specific test category python -m pytest tests/test_task_management.py # Run with coverage python -m pytest --cov=src/bmad_mcp tests/

📚 Documentation

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

See CONTRIBUTING.md for detailed guidelines.

📈 Roadmap

✅ Recently Completed (v2.1)

  • Time & Cost Tracking System: Precise project billing with AI cost calculation ⭐ NEW!
  • BMAD-METHOD Workflow System: Complete workflow implementation with intelligent orchestration
  • Quality Gates System: All 6 @qa commands (*risk, *design, *trace, *nfr, *review, *gate)
  • Serena Bridge Agent: LSP-based semantic code intelligence integration
  • Agent Coordination: 6-agent ecosystem with smart routing and collaboration
  • Template-System: 6 standardized project templates
  • Auto-Discovery: Automatic project detection and integration
  • Migration Tools: Legacy project migration to BMAD v2.0
  • Standardized Structure: Unified .bmad-core/ project layout

🔄 In Progress (v2.2)

  • Workflow Automation: Advanced automation rules and triggers
  • Multi-Project Workflows: Cross-project dependency management
  • Enhanced Analytics: Workflow performance insights and optimization
  • Custom Quality Gates: User-definable quality criteria and checks

🚀 Planned Features (v3.0)

  • Web Dashboard: Browser-based workflow management interface
  • Team Collaboration: Multi-user project support with role-based access
  • Enterprise Workflows: Advanced enterprise features and compliance
  • Serena Enhancements: Multi-language LSP support and AI-assisted refactoring
  • Plugin System: Custom agent and quality gate development
  • Mobile App: Companion mobile application for workflow monitoring
  • Template Marketplace: Community-driven template sharing platform

🔐 Security

  • All API keys managed via environment variables
  • No secrets stored in code or configuration files
  • Secure MCP protocol communication
  • Optional token rotation and audit logging

See SECURITY.md for security guidelines.

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

💬 Support

🙏 Acknowledgments

Made with ❤️ for developers who love intelligent task management

This server cannot be installed

-
security - not tested
A
license - permissive license
-
quality - not tested

How are these scores calculated?

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

Provides intelligent agent routing with 5 specialized AI agents (analyst, architect, dev, pm, qa) through OpenRouter integration. Enables unified project structure across all IDEs with global registry management and automated BMAD methodology workflows.

  1. ✨ Features
    1. 🤖 6 Specialized AI Agents
    2. 📋 Advanced Task Management
    3. ⏱️ Time & Cost Tracking ⭐ NEW!
    4. 🎨 Template-System & Standardisierte Projektstrukturen ⭐ NEW!
    5. 🔄 Enhanced Features
    6. 🌐 Universal IDE Access
  2. 🚀 Quick Start
    1. Prerequisites
    2. Installation
    3. Configuration
  3. 🛠️ Available MCP Tools
    1. 🤖 Agent Management
    2. 📋 Task Management
    3. ⏱️ Time & Cost Tracking ⭐ NEW!
    4. ⚡ Enhanced Features
    5. 🔧 Project Management
    6. 🚀 BMAD-METHOD Workflow System ⭐ NEW!
    7. 🔍 Semantic Code Analysis ⭐ NEW!
    8. 🎨 Template-System ⭐ NEW!
  4. 📊 Usage Examples
    1. Basic Task Management
    2. Real-time Monitoring
    3. Time & Cost Tracking ⭐ NEW!
    4. Project Context
    5. Template-System Usage ⭐ NEW!
    6. Available Templates
    7. Simulation & Testing
    8. Advanced Time Tracking Workflows ⭐ NEW!
  5. 🏗️ Architecture
    1. 🔧 Configuration
      1. Environment Variables
      2. Agent Configuration
    2. 🐳 Docker Deployment
      1. 🧪 Testing
        1. 📚 Documentation
          1. 🤝 Contributing
            1. 📈 Roadmap
              1. ✅ Recently Completed (v2.1)
              2. 🔄 In Progress (v2.2)
              3. 🚀 Planned Features (v3.0)
            2. 🔐 Security
              1. 📝 License
                1. 💬 Support
                  1. 🙏 Acknowledgments

                    Related MCP Servers

                    • OpenRouter MCP Server

                      heltonteixeira
                      A
                      security
                      A
                      license
                      A
                      quality
                      Provides integration with OpenRouter.ai, allowing access to various AI models through a unified interface.
                      Last updated -
                      28
                      57
                      Apache 2.0

                    • MCP Architect

                      squirrelogic
                      A
                      security
                      A
                      license
                      A
                      quality
                      Facilitates comprehensive architectural design and evaluation through specialized agents, rich resources, and powerful tools covering diverse architectural domains, including cloud, AI, and blockchain.
                      Last updated -
                      3
                      1,406
                      27
                      ISC License

                    • MindBridge MCP Server

                      pinkpixel-dev
                      A
                      security
                      A
                      license
                      A
                      quality
                      An AI router that connects applications to multiple LLM providers (OpenAI, Anthropic, Google, DeepSeek, Ollama, etc.) with smart model orchestration capabilities, enabling dynamic switching between models for different reasoning tasks.
                      Last updated -
                      3
                      54
                      19
                      MIT License
                      • Linux
                      • Apple

                    • BMAD Agent FastMCP Service

                      2799662352
                      -
                      security
                      A
                      license
                      -
                      quality
                      A professional AI agent system that provides 10+ specialized agents and 25+ MCP tools to support development workflows in Cursor IDE, with dual LLM mode support (built-in and DeepSeek API).
                      Last updated -
                      2
                      MIT License

                    View all related MCP servers

                    New MCP Servers

                    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/Dali1789/bmad-mcp-server'

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