tosin2013/mcp-adr-analysis-server

MCP ADR Analysis Server

AI-powered architectural analysis for intelligent development workflows. Returns actual analysis results, not prompts to submit elsewhere.

TL;DR

What: MCP server that provides AI-powered architectural decision analysis and ADR management
Who: AI coding assistants (Claude, Cline, Cursor), enterprise architects, development teams
Why: Get immediate architectural insights instead of prompts, with 95% confidence scoring
How: npm install -g mcp-adr-analysis-server → Configure with OpenRouter API → Start analyzing

Key Features: Tree-sitter AST analysis • Security content masking • Test-driven development • Deployment readiness validation

Author: Tosin Akinosho | Repository: GitHub

What is MCP?

The Model Context Protocol enables seamless integration between AI assistants and external tools. This server enhances AI assistants with deep architectural analysis capabilities, enabling intelligent code generation, decision tracking, and development workflow automation.

✨ Core Capabilities

🤖 AI-Powered Analysis - Immediate architectural insights with OpenRouter.ai integration 🏗️ Technology Detection - Identify any tech stack and architectural patterns 📋 ADR Management - Generate, suggest, and maintain Architectural Decision Records 🔗 Smart Code Linking - AI-powered discovery of code files related to ADRs and decisions 🛡️ Security & Compliance - Detect and mask sensitive content automatically 🧪 TDD Integration - Two-phase Test-Driven Development with validation 🚀 Deployment Readiness - Zero-tolerance test validation with hard blocking

📖

📦 Quick Installation

# Global installation (recommended)
npm install -g mcp-adr-analysis-server

# RHEL 9/10 systems (special installer)
curl -sSL https://raw.githubusercontent.com/tosin2013/mcp-adr-analysis-server/main/scripts/install-rhel.sh | bash

📖 |

⚡ Quick Setup (3 Steps)

1. Get API Key: OpenRouter.ai/keys
2. Set Environment: OPENROUTER_API_KEY=your_key + EXECUTION_MODE=full
3. Configure Client: Add to Claude Desktop, Cline, Cursor, or Windsurf

{
  "mcpServers": {
    "adr-analysis": {
      "command": "mcp-adr-analysis-server",
      "env": {
        "PROJECT_PATH": "/path/to/your/project",
        "OPENROUTER_API_KEY": "your_key_here",
        "EXECUTION_MODE": "full"
      }
    }
  }
}

📖 |

🚀 Usage Examples

Ask Claude (or any MCP client):

"Analyze this React project's architecture and suggest ADRs for any implicit decisions"

"Generate ADRs from the PRD.md file and create a todo.md with implementation tasks"

"Check this codebase for security issues and provide masking recommendations"

The server returns actual analysis results instead of prompts to submit elsewhere!

// Basic project analysis
const analysis = await analyzeProjectEcosystem({
  projectPath: '/path/to/project',
  analysisType: 'comprehensive',
});

// Generate ADRs from requirements
const adrs = await generateAdrsFromPrd({
  prdPath: 'docs/PRD.md',
  outputDirectory: 'docs/adrs',
});

// Smart Code Linking - Find code related to ADR decisions
const relatedCode = await findRelatedCode(
  'docs/adrs/001-auth-system.md',
  'We will implement JWT authentication with Express middleware',
  '/path/to/project',
  {
    useAI: true, // AI-powered keyword extraction
    useRipgrep: true, // Fast text search
    maxFiles: 10, // Limit results
    includeContent: true, // Include file contents
  }
);

📖 |

🎯 Use Cases

👨‍💻 AI Coding Assistants - Enhance Claude, Cline, Cursor with architectural intelligence
💬 Conversational AI - Answer architecture questions with confidence scoring
🤖 Autonomous Agents - Continuous analysis and rule enforcement
🏢 Enterprise Teams - Portfolio analysis and migration planning

📖

🛠️ Technology Stack

Runtime: Node.js 20+ • Language: TypeScript • Framework: MCP SDK • Testing: Jest (>80% coverage) Search: ripgrep + fast-glob • AI Integration: OpenRouter.ai • Web Research: Firecrawl • Code Analysis: Smart Code Linking

📖

📁 Project Structure

src/tools/     # 23 MCP tools for analysis
docs/adrs/     # Architectural Decision Records
tests/         # >80% test coverage
.github/       # CI/CD automation

📖

🧪 Testing

npm test              # Run all tests (>80% coverage)
npm run test:coverage # Coverage report

📖

🔥 Firecrawl Integration (Optional)

Enhanced web research capabilities for comprehensive architectural analysis.

# Option 1: Cloud service (recommended)
export FIRECRAWL_ENABLED="true"
export FIRECRAWL_API_KEY="fc-your-api-key-here"

# Option 2: Self-hosted
export FIRECRAWL_ENABLED="true"
export FIRECRAWL_BASE_URL="http://localhost:3000"

# Option 3: Disabled (default - server works without web search)

Benefits: Real-time research • Enhanced ADRs • Best practices discovery • Intelligent web scraping

📖

🔧 Development

git clone https://github.com/tosin2013/mcp-adr-analysis-server.git
cd mcp-adr-analysis-server
npm install && npm run build && npm test

Quality Standards: TypeScript strict mode • ESLint • >80% test coverage • Pre-commit hooks

📖 |

🔧 Troubleshooting

Common Issues:

• RHEL Systems: Use special installer script
• Tools return prompts: Set EXECUTION_MODE=full + API key
• Module not found: Run npm install && npm run build
• Permission denied: Check file permissions and project path

📖

🔒 Security & Performance

Security: Automatic secret detection • Content masking • Local processing • Zero trust
Performance: Multi-level caching • Incremental analysis • Parallel processing • Memory optimization

📖 |

🤝 Contributing

We welcome contributions! Fork → Create branch → Add tests → Submit PR

Standards: TypeScript strict • >80% coverage • ESLint • Security validation • MCP compliance

📖

🔗 Resources

Official: MCP Specification • MCP SDK
Community: MCP Registry • Discord
Project: • •

📄 License

MIT License - see file for details.

🙏 Acknowledgments

• Anthropic for creating the Model Context Protocol
• The MCP Community for inspiration and best practices
• Contributors who help make this project better

Built with ❤️ by Tosin Akinosho for AI-driven architectural analysis

Empowering AI assistants with deep architectural intelligence and decision-making capabilities.