Skip to main content

MCP ADR Analysis Server

AI-powered architectural analysis for intelligent development workflows

An MCP server that gives AI coding assistants โ€” Claude, Cursor, Cline, Windsurf โ€” deep architectural analysis capabilities. Unlike other tools, it returns actual analysis results with confidence scoring, not prompts to submit elsewhere.

npm install -g mcp-adr-analysis-server

โœจ Core Capabilitiesโ€‹

๐Ÿค– AI-Powered Analysis โ€” Immediate architectural insights via OpenRouter.ai integration

๐Ÿ“‹ ADR Management โ€” Generate, suggest, and maintain Architectural Decision Records automatically

๐Ÿ”— Smart Code Linking โ€” AI-powered discovery of code files related to ADRs and decisions

๐Ÿ—๏ธ Technology Detection โ€” Identify any tech stack and architectural patterns in your codebase

๐Ÿ›ก๏ธ Security & Compliance โ€” Detect and mask sensitive content with configurable patterns

๐Ÿš€ Deployment Readiness โ€” Zero-tolerance test validation with hard blocking before deploy

๐Ÿงช TDD Integration โ€” Two-phase Test-Driven Development with automated validation


๐ŸŽฏ Who Is This For?โ€‹

๐Ÿ‘จโ€๐Ÿ’ป AI Assistant Usersโ€‹

Use with Claude Desktop, Cline, Cursor, or Windsurf to enhance your AI coding workflow with architectural intelligence. Ask questions in natural language and get real analysis results back.

๐Ÿข Enterprise Architectsโ€‹

Track architectural decisions with ADRs, build knowledge graphs across repositories, enforce compliance standards, and generate governance reports โ€” all integrated into your existing toolchain.

๐Ÿ› ๏ธ Development Teamsโ€‹

Integrate into CI/CD pipelines for automated code quality checks, deployment readiness validation, security scanning, and test coverage enforcement with >80% thresholds.


โšก Quick Startโ€‹

1. Installโ€‹

npm install -g mcp-adr-analysis-server

2. Get an API Key (optional)โ€‹

Sign up at OpenRouter.ai/keys for full AI-powered analysis. No API key? The server still works in prompt-only mode โ€” you'll get prompts you can paste into any AI chat.

3. Configure Your MCP Clientโ€‹

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

See the Installation Guide for detailed setup instructions, client-specific config locations, and troubleshooting.


๐Ÿ“š Explore the Docsโ€‹

๐ŸŽ“ Tutorialsโ€‹

Step-by-step guides to get you up and running โ€” from first install to your first architectural analysis.

๐Ÿ› ๏ธ How-To Guidesโ€‹

Task-oriented recipes for specific goals: configuring clients, running analyses, managing ADRs, and integrating with CI/CD.

๐Ÿ“– Referenceโ€‹

Technical details on all 23 MCP tools, environment variables, configuration options, and API specifications.

๐Ÿ’ก Explanationโ€‹

Deep dives into architectural concepts, design decisions, security philosophy, and how the server works under the hood.