The MCP server provides AI-powered architectural decision analysis and ADR management for development workflows. It integrates with AI assistants to deliver immediate architectural insights and decision tracking.
From the registry: AI-powered MCP server for analyzing Architectural Decision Records (ADRs).
Please install the `mcp-adr-analysis-server` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js 20+** — Node.js 20 or higher
Optional prerequisites:
- OpenRouter API key — Sign up at openrouter.ai/keys (https://openrouter.ai/keys)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["mcp-adr-analysis-server"]
- required environment variables:
- `PROJECT_PATH`: Absolute path to the project to analyze (example: `/path/to/your/project`)
- `OPENROUTER_API_KEY`: OpenRouter API key (optional; without it, server runs in prompt-only mode) (example: `<your-api-key>`)
- optional environment variables:
- `EXECUTION_MODE`: Set to 'full' for AI-powered analysis (example: `full`)
- `ADR_AGGREGATOR_API_KEY`: Optional ADR Aggregator API key (example: `<your-api-key>`)
- `FIRECRAWL_API_KEY`: Optional Firecrawl API key for web scraping (example: `<your-api-key>`)
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.OPENROUTER_API_KEYrequiredAPI key for accessing OpenRouter services.EXECUTION_MODErequiredMode of operation for the server, either 'full' for full features or 'prompt-only' for limited functionality.AI Agents Framework with Self Reflection and MCP support