Skip to content
Arxo Arxo

MCP

The Arxo MCP (Model Context Protocol) server exposes agent architecture analysis to AI assistants such as Cursor and Claude. Use it to run analyses on agent and LLM-powered code, get reliability and governance metrics, and manage your arxo.yaml configuration from your IDE or chat.

The MCP server analyzes TypeScript and Python for agent architecture. Create an arxo.yaml in your project root (optional) to configure analysis; see Configuration for config options.

Use caseBest option
Chat-driven analysis (“Run agent architecture analysis on this project”)MCP — AI calls tools on demand
Pre-commit hooks, CI/CD pipelinesCLIarxo analyze
Real-time analysis as you code, inline violationsIDE extension — Arxo VS Code extension

MCP is ideal when you want to ask natural-language questions and get agent architecture insights within the AI chat, without leaving your editor.

  • Agent and OpenClaw architecture analysis — Run analysis to get reliability, governance, safety, and coordination metrics for agent/LLM code and OpenClaw config/skill/observability metrics
  • Config help — Get schema, validate config, or generate a suggested arxo.yaml for your project

You install the arxo-mcp binary and configure your MCP client (e.g. Cursor) to run it. The server communicates over stdio using the Model Context Protocol. AI assistants can then call analyze_architecture to run analysis or use the config tools to work with arxo.yaml.