Deterministically analyzes a local code repository to extract its architecture, routes, domain models, security findings, and a production-readiness score, writing the results to files under .archiet/. It also exposes the extracted repository model through an MCP server so agents can query blast radius, architecture summaries, findings, diagrams, and readiness information.
From the registry: Submit architecture docs, get a consulting-grade traceability audit at a shareable URL
$ pip install archiet-xrayPlease install the `archiet-audit` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Python package** — Install the Archiet X-Ray package so the `archiet-xray` command is available. Run: `pip install archiet-xray`
Canonical MCP server config (stdio transport):
- command: `archiet-xray`
- args: ["mcp","<path-to-repo>"]
Note: README also shows an alternative portable install path via `uvx` in the install badge/deeplink (`uvx archiet-xray mcp`), but the explicit CLI example uses the installed `archiet-xray mcp /path/to/repo` form. The MCP server requires a repository path argument at configuration time. No environment variables are documented.
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.Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.