shipcheck-mcp

<p align="center"> <img src="docs/images/hero.png" alt="ShipCheck — MCP verification server" width="820"> </p> <h1 align="center">ShipCheck</h1> <p align="center"><b>It doesn't write tests. It proves the feature works.</b></p> <p align="center"> <a href="#"><img alt="license" src="https://img.shields.io/badge/license-MIT-blue"></a> <a href="#"><img alt="tests" src="https://img.shields.io/badge/tests-172%20passing-brightgreen"></a> <a href="#"><img alt="mcp tools" src="https://img.shields.io/badge/MCP%20tools-27-2e5aa8"></a> </p> --- ## In a nutshell AI coding agents (Claude Code, Cursor, OpenCode…) can write code and write tests, but nothing checks the agent's own work the way a QA engineer would: actually run the app, click through the real flow, hit the real API, and look at the real database. ShipCheck is that QA engineer, exposed as an MCP server. Point it at any repository and describe a feature — it **discovers** how the app actually works (no hardcoded assumptions about routes, tables, or auth patterns), **plans** what to check, and **verifies** it across the UI, the API, and the database, handing back evidence instead of a guess. ``` ANY SOFTWARE │ ▼ INSPECT · DISCOVER detect stack, build a SystemGraph of routes/tables/actors │ ▼ PLAN generate a verification plan from the graph — no hardcoded URLs │ ▼ VERIFY Playwright (UI) + HTTP (API) + read-only SQL (database) │ ▼ EVIDENCE pass/fail per layer, diagnosis on failure, a written report ``` ## Install Published on PyPI as `shipcheck-mcp` (the import name is still `shipcheck`, the MCP server and CLI are the same package — `mcp` is a base dependency, not an extra, so the plain command below is enough to run the MCP server): ```bash pip install shipcheck-mcp # MCP server + CLI, no extras needed pip install 'shipcheck-mcp[playwright,database]' # …