Archy analyzes Python codebases by building a module-dependency graph and reporting structural health through scores, cycles, layer checks, contracts, hotspots, and impacted tests/modules. It can run as an MCP server to expose these checks to AI coding agents and supports caching plus agent installation for tools like Claude Code and Cursor.
From the registry: Architectural sensor for Python codebases.

$ pip install archyhttps://docs.astral.sh/uv/Please install the `archy` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Python 3.10+** — Archy requires Python 3.10 or newer. (https://pypi.org/project/archy/)
Optional prerequisites:
- Install uv or pip/pipx — Install Archy via uv, pip, or pipx. The README recommends uv for the easiest MCP setup path. Run: `pip install archy` (https://docs.astral.sh/uv/)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["archy","mcp"]
Note: The README presents `archy mcp` as the MCP server entrypoint and explicitly states it uses stdio transport. For the most portable no-clone setup, prefer `uvx archy mcp`. Alternative install/run paths mentioned are `pip install archy` then `archy mcp`, `uv tool install archy`, or `pipx install archy`. No environment variables are required for the MCP server itself.
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.Trending hip-hop artist momentum scores across four cultural dimensions.
Official PostHog MCP Server for product analytics, feature flags, experiments, and more.
Official OpenMetadata MCP: governed context and business semantics for AI assistants and agents.