Claude Agents Power Mcp Server

🤖 Claude Agents Power

[](README.md) [](README.kr.md) [](LICENSE) [](https://www.typescriptlang.org/) [](https://modelcontextprotocol.org/)

> 🎯 Smart Role Assignment for Development Teams - An intelligent MCP server that analyzes your project and recommends the perfect team composition from 100+ professional roles across all company departments.

🚀 Quick Start with Claude

1️⃣ Install & Configure MCP Server

# Install via npm
npm install -g claude-agents-power

# Automatically configure Claude Desktop (NEW! 🎉)
# claude-agents-power --install

Or manually configure Claude Desktop:

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "claude-agents-power": {
      "command": "claude-agents-power"
    }
  }
}

2️⃣ Usage in Claude

Open Claude and try this example:

👤 User: "claude-agents-power를 이용해서 이 프로젝트를 위한 추천 및 agents/*.md 파일을 다운로드 해줘"

🤖 Claude: I'll analyze your project and download the recommended agents for you.

[Uses MCP tools to:]
1. 📊 Analyze your project structure 
2. 🎯 Recommend suitable roles
3. 📁 Download agents to ./claude/agents/
4. ✅ Ready to use sub-agents for your project!

3️⃣ Verify Installation

Check that agents were downloaded:

ls ./claude/agents/
# You should see downloaded .md files for recommended roles

4️⃣ Start Using Sub-Agents

Now you can use specialized roles in Claude:

"frontend-developer를 사용해서 React 컴포넌트를 만들어줘"
"data-scientist로 이 데이터를 분석해줘"  
"devops-engineer가 CI/CD 파이프라인을 설정해줘"

---

📖 Table of Contents

• [🌟 Features](#-features)
• [🚀 Quick Start](#-quick-start)
• [📋 Available Roles](#-available-roles)
• [⚡ Slash Commands (NEW!)](#-slash-commands-new)
• [🎯 Usage Examples](#-usage-examples)
• [📚 Documentation](#-documentation)
• [🛠️ Development](#-development)
• [🤝 Contributing](#-contributing)
• [📄 License](#-license)

🌟 Features

🔍 Intelligent Project Analysis

• Automatically detects project type, frameworks, and complexity
• Provides smart role recommendations based on your tech stack
• Supports multi-language projects and diverse architectures

👥 100+ Professional Roles

• Technology & Engineering (20 roles): Frontend, Backend, DevOps, Security, AI/ML
• Data & Analytics (15 roles): Data Scientists, Analysts, Engineers
• Product & Design (10 roles): PM, UX/UI Designers, Researchers
• Marketing & Sales (10 roles): Digital Marketing, Growth, Content
• Operations & Management (15 roles): Project Managers, Operations
• Finance & Accounting (10 roles): CFO, Controllers, Analysts
• Human Resources (10 roles): Talent Acquisition, L&D, Culture
• Executive & Leadership (10 roles): C-Level executives and strategy

🌐 Multi-Language Support

• English: Global standards and international projects
• 한국어: Korean business context and local practices

⚡ Claude Code Integration

• Seamless integration with Claude Code via MCP protocol
• Real-time role recommendations and team composition
• One-click agent installation to your project

🌐 GitHub Integration

• Automatic agent downloading from baryonlabs/claude-sub-agent-contents
• Download tracking and usage analytics
• Offline caching for downloaded agents
• Installs to ./claude/agents/ directory structure
• No need to create agent templates from scratch

🚀 Development Setup

Build from Source

# Clone the repository
git clone https://github.com/hongsw/claude-agents-power-mcp-server.git
cd claude-agents-power

# Install dependencies
npm install

# Build the project
npm run build

MCP Configuration for Development

Add to your ~/.config/claude/mcp_servers.json:

{
  "mcpServers": {
    "claude-agents-power": {
      "command": "node",
      "args": ["/path/to/claude-agents-power/dist/index.js"],
      "cwd": "/path/to/your/project",
      "env": {
        "GITHUB_TOKEN": "your_github_token_here"
      }
    }
  }
}

Analytics & Telemetry

This tool includes anonymous usage analytics (telemetry) to help improve the user experience and identify common usage patterns. The telemetry system:

• What is collected: Tool usage patterns, command frequency, error rates (no personal data)
• What is NOT collected: File contents, agent data, GitHub tokens, or any personally identifiable information
• Purpose: Understanding which features are most used, identifying common errors, improving performance
• Technology: Uses PostHog with a public API key that can only send events, not read data

Disabling Telemetry

If you prefer not to send anonymous usage data, you can disable telemetry using either of these methods:

# Method 1: Environment variable
export DISABLE_TELEMETRY=true

# Method 2: In your .env file
DISABLE_TELEMETRY=true

# Alternative (also works)
DISABLE_ANALYTICS=true

Telemetry vs OpenTelemetry

This project uses product analytics telemetry (PostHog), not OpenTelemetry:

• Product Analytics Telemetry: Tracks user interactions, feature usage, and product metrics
• OpenTelemetry: Industry standard for distributed tracing, metrics, and logs in microservices

While both involve "telemetry", they serve different purposes. Our telemetry helps understand how the tool is used to improve the user experience, not for system monitoring or performance tracing.

Environment Variables

Configure these optional environment variables for enhanced functionality:

Method 1: Using .env file (Recommended for local development)

1. Copy the example environment file:

``bash cp .env.example .env ``

1. Edit .env and add your GitHub token:

```bash # GitHub Personal Access Token (required for auto issue creation) GITHUBTOKEN=ghpyouractualtoken_here

# To disable analytics, uncomment: # DISABLE_ANALYTICS=true ```

Method 2: Using MCP configuration

Add environment variables directly to your MCP server configuration as shown above.

Available Variables

• GITHUB_TOKEN: GitHub personal access token for automatic issue creation when agents are not found
• Create at: https://github.com/settings/tokens
• Required permissions: public_repo or repo (for private repos)

• DISABLE_TELEMETRY or DISABLE_ANALYTICS: Set to true to disable anonymous usage telemetry
• Telemetry is enabled by default to help improve the tool
• No personal data is collected, only anonymous usage metrics
• Example: DISABLE_TELEMETRY=true

• POSTHOG_API_KEY: Custom PostHog API key (optional)
• The tool includes a default public key for analytics
• Only set if you want to use your own PostHog project

• POSTHOG_HOST: PostHog instance URL (defaults to https://app.posthog.com)
• Only needed if using a self-hosted PostHog instance

MCP Tools Reference

# Analyze your current project
mcp__claude-agents-power__analyze-project

# Get role recommendations  
mcp__claude-agents-power__recommend-by-keywords ["web", "api", "database"]

# Install recommended agents
mcp__claude-agents-power__install-agents ["frontend-developer", "backend-developer"]

📋 Available Roles

🔧 Technology & Engineering (20 roles)

| Role | English | 한국어 | Tools | Specialization | |------|---------|--------|-------|----------------| | [Software Engineer](sub-agents/en/software-engineer.md) | [EN](sub-agents/en/software-engineer.md) | [KO](sub-agents/ko/software-engineer.md) | Bash, Read, Write, Edit | Full-stack development, system design | | [Frontend Developer](sub-agents/en/frontend-developer.md) | [EN](sub-agents/en/frontend-developer.md) | [KO](sub-agents/ko/frontend-developer.md) | Read, Write, Edit, Bash | React, Vue, Angular, UI/UX | | [Backend Developer](sub-agents/en/backend-developer.md) | [EN](sub-agents/en/backend-developer.md) | [KO](sub-agents/ko/backend-developer.md) | Bash, Read, Write, Edit | APIs, databases, server architecture | | [DevOps Engineer](sub-agents/en/devops-engineer.md) | [EN](sub-agents/en/devops-engineer.md) | [KO](sub-agents/ko/devops-engineer.md) | Bash, Read, Write | CI/CD, infrastructure automation | | [Data Engineer](sub-agents/en/data-engineer.md) | [EN](sub-agents/en/data-engineer.md) | [KO](sub-agents/ko/data-engineer.md) | Bash, Read, Write | ETL pipelines, data architecture |

📱 View All Technology Roles (15 more)

| Role | English | 한국어 | Tools | Specialization | |------|---------|--------|-------|----------------| | [ML Engineer](sub-agents/en/machine-learning-engineer.md) | [EN](sub-agents/en/machine-learning-engineer.md) | [KO](sub-agents/ko/machine-learning-engineer.md) | Bash, Read, Write | Model deployment, MLOps | | [Security Engineer](sub-agents/en/security-engineer.md) | [EN](sub-agents/en/security-engineer.md) | [KO](sub-agents/ko/security-engineer.md) | Bash, Read, Grep | Cybersecurity, threat analysis | | [Cloud Architect](sub-agents/en/cloud-architect.md) | [EN](sub-agents/en/cloud-architect.md) | [KO](sub-agents/ko/cloud-architect.md) | Bash, Read, Write | AWS, Azure, GCP architecture | | [Mobile Developer](sub-agents/en/mobile-developer.md) | [EN](sub-agents/en/mobile-developer.md) | [KO](sub-agents/ko/mobile-developer.md) | Read, Write, Edit, Bash | iOS, Android, React Native | | [QA Engineer](sub-agents/en/qa-engineer.md) | [EN](sub-agents/en/qa-engineer.md) | [KO](sub-agents/ko/qa-engineer.md) | Bash, Read, Write | Test automation, quality assurance | | [Database Administrator](sub-agents/en/database-administrator.md) | [EN](sub-agents/en/database-administrator.md) | [KO](sub-agents/ko/database-administrator.md) | Bash, Read, Write | Database optimization, backup | | [Network Engineer](sub-agents/en/network-engineer.md) | [EN](sub-agents/en/network-engineer.md) | [KO](sub-agents/ko/network-engineer.md) | Bash, Read, Write | Network infrastructure, security | | [Site Reliability Engineer](sub-agents/en/site-reliability-engineer.md) | [EN](sub-agents/en/site-reliability-engineer.md) | [KO](sub-agents/ko/site-reliability-engineer.md) | Bash, Read, Write | System reliability, monitoring | | [Blockchain Developer](sub-agents/en/blockchain-developer.md) | [EN](sub-agents/en/blockchain-developer.md) | [KO](sub-agents/ko/blockchain-developer.md) | Read, Write, Edit | Smart contracts, DeFi | | [Game Developer](sub-agents/en/game-developer.md) | [EN](sub-agents/en/game-developer.md) | [KO](sub-agents/ko/game-developer.md) | Read, Write, Edit | Unity, Unreal, game engines | | [Embedded Systems Engineer](sub-agents/en/embedded-systems-engineer.md) | [EN](sub-agents/en/embedded-systems-engineer.md) | [KO](sub-agents/ko/embedded-systems-engineer.md) | Read, Write, Bash | IoT, firmware, hardware | | [Technical Writer](sub-agents/en/technical-writer.md) | [EN](sub-agents/en/technical-writer.md) | [KO](sub-agents/ko/technical-writer.md) | Read, Write, Edit | Documentation, API docs | | [Solution Architect](sub-agents/en/solution-architect.md) | [EN](sub-agents/en/solution-architect.md) | [KO](sub-agents/ko/solution-architect.md) | Read, Write, Bash | System integration, design | | [AI Researcher](sub-agents/en/ai-researcher.md) | [EN](sub-agents/en/ai-researcher.md) | [KO](sub-agents/ko/ai-researcher.md) | Read, Write, Bash | Research, algorithm development | | [Tech Lead](sub-agents/en/tech-lead.md) | [EN](sub-agents/en/tech-lead.md) | [KO](sub-agents/ko/tech-lead.md) | Read, Write, Edit, Bash | Team leadership, architecture |

📊 Data & Analytics (15 roles)

| Role | English | 한국어 | Tools | Specialization | |------|---------|--------|-------|----------------| | [Data Scientist](sub-agents/en/data-scientist.md) | [EN](sub-agents/en/data-scientist.md) | [KO](sub-agents/ko/data-scientist.md) | Bash, Read, Write | ML modeling, statistical analysis | | [Data Analyst](sub-agents/en/data-analyst.md) | [EN](sub-agents/en/data-analyst.md) | [KO](sub-agents/ko/data-analyst.md) | Read, Write, Bash | Business insights, reporting | | [Business Intelligence Analyst](sub-agents/en/business-intelligence-analyst.md) | [EN](sub-agents/en/business-intelligence-analyst.md) | [KO](sub-agents/ko/business-intelligence-analyst.md) | Read, Write, Bash | Dashboards, BI tools | | [Quantitative Analyst](sub-agents/en/quantitative-analyst.md) | [EN](sub-agents/en/quantitative-analyst.md) | [KO](sub-agents/ko/quantitative-analyst.md) | Read, Write, Bash | Financial modeling, risk analysis | | [Research Analyst](sub-agents/en/research-analyst.md) | [EN](sub-agents/en/research-analyst.md) | [KO](sub-agents/ko/research-analyst.md) | Read, Write | Market research, competitive analysis |

📈 View All Data & Analytics Roles (10 more)

| Role | English | 한국어 | Tools | Specialization | |------|---------|--------|-------|----------------| | [Analytics Engineer](sub-agents/en/analytics-engineer.md) | [EN](sub-agents/en/analytics-engineer.md) | [KO](sub-agents/ko/analytics-engineer.md) | Bash, Read, Write | Data infrastructure, modeling | | [Marketing Analyst](sub-agents/en/marketing-analyst.md) | [EN](sub-agents/en/marketing-analyst.md) | [KO](sub-agents/ko/marketing-analyst.md) | Read, Write | Campaign optimization, metrics | | [Financial Analyst](sub-agents/en/financial-analyst.md) | [EN](sub-agents/en/financial-analyst.md) | [KO](sub-agents/ko/financial-analyst.md) | Read, Write | Financial planning, forecasting | | [Operations Analyst](sub-agents/en/operations-analyst.md) | [EN](sub-agents/en/operations-analyst.md) | [KO](sub-agents/ko/operations-analyst.md) | Read, Write, Bash | Process optimization, efficiency | | [Product Analyst](sub-agents/en/product-analyst.md) | [EN](sub-agents/en/product-analyst.md) | [KO](sub-agents/ko/product-analyst.md) | Read, Write | User behavior, product metrics | | [Risk Analyst](sub-agents/en/risk-analyst.md) | [EN](sub-agents/en/risk-analyst.md) | [KO](sub-agents/ko/risk-analyst.md) | Read, Write | Risk assessment, mitigation | | [Growth Analyst](sub-agents/en/growth-analyst.md) | [EN](sub-agents/en/growth-analyst.md) | [KO](sub-agents/ko/growth-analyst.md) | Read, Write | Growth metrics, experimentation | | [Customer Insights Analyst](sub-agents/en/customer-insights-analyst.md) | [EN](sub-agents/en/customer-insights-analyst.md) | [KO](sub-agents/ko/customer-insights-analyst.md) | Read, Write | Customer segmentation, behavior | | [Pricing Analyst](sub-agents/en/pricing-analyst.md) | [EN](sub-agents/en/pricing-analyst.md) | [KO](sub-agents/ko/pricing-analyst.md) | Read, Write | Pricing strategy, revenue optimization | | [Supply Chain Analyst](sub-agents/en/supply-chain-analyst.md) | [EN](sub-agents/en/supply-chain-analyst.md) | [KO](sub-agents/ko/supply-chain-analyst.md) | Read, Write, Bash | Supply chain optimization |

🎨 Product & Design (10 roles)

| Role | English | 한국어 | Tools | Specialization | |------|---------|--------|-------|----------------| | [Product Manager](sub-agents/en/product-manager.md) | [EN](sub-agents/en/product-manager.md) | [KO](sub-agents/ko/product-manager.md) | Read, Write | Product strategy, roadmap | | [Product Designer](sub-agents/en/product-designer.md) | [EN](sub-agents/en/product-designer.md) | [KO](sub-agents/ko/product-designer.md) | Read, Write | User experience, product design | | [UX Designer](sub-agents/en/ux-designer.md) | [EN](sub-agents/en/ux-designer.md) | [KO](sub-agents/ko/ux-designer.md) | Read, Write | User research, wireframes | | [UI Designer](sub-agents/en/ui-designer.md) | [EN](sub-agents/en/ui-designer.md) | [KO](sub-agents/ko/ui-designer.md) | Read, Write | Visual design, prototypes | | [Graphic Designer](sub-agents/en/graphic-designer.md) | [EN](sub-agents/en/graphic-designer.md) | [KO](sub-agents

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: hongsw
• Source: hongsw/claude-agents-power-mcp-server
• License: MIT
• Homepage: https://www.npmjs.com/package/claude-agents-power

Install and usage instructions live in the source repository linked above.