Recursively scans a project directory (React Native, web, Flutter, or backend) for API endpoints — fetch/axios/Dart-http/Dio client calls and Express/NestJS/Flask/FastAPI/Spring server routes. Writes a discovery report and endpoints.json.

Searches the project for an existing OpenAPI/Swagger document (swagger.json, openapi.yaml, etc.) and reports what was found.

Builds an OpenAPI 3.0 spec from discovered endpoints. If an existing spec is found and useExisting is true, it is loaded instead of regenerated. Writes the spec into the project's .api-mcp directory.

Generates a test plan (happy-path, edge, negative, and security cases) for every discovered endpoint, based on its HTTP method and parameters. Writes tests.json. Does not execute anything.

Generates the test plan and executes it against the running server (like Postman). Saves full responses to results.json and a Markdown report. Requires baseUrl unless endpoints use absolute URLs.

One-call pipeline: scans for endpoints, generates/loads an OpenAPI spec, generates test + edge cases, executes them against the live server, and writes all reports. Provide baseUrl and auth so execution can reach the server.

Regenerates the HTML report and a colorful, multi-sheet XLSX spreadsheet from previously saved endpoints.json / results.json (in the project's .api-mcp folder). Use this to get shareable HTML/Excel output without re-running the tests.

Scans config (.env), axios/Dart baseURL settings, and absolute URLs in the code to find candidate API base URLs. Works for web and mobile apps. QA can use the top candidate or override it.

Given a base URL and credentials, auto-detects the login endpoint, posts the credentials (trying email/username field variants), and extracts the token from the response. Returns the token and reports exactly what worked.

The QA one-call workflow. Provide the project path and a list of role credentials (email/username + password). The tool detects the base URL and login endpoint, logs in as each role, runs the test suite per role (read-only by default), and writes a per-role + combined report. Set includeWrites=true only against a throwaway/staging env.