Trigger App Crawl
trigger_crawlSystematically explore web app pages, UI states, and navigation flows to build a project knowledge graph. Supports localhost URLs via automatic tunnel. Returns crawl execution status.
Instructions
Trigger a browser-agent crawl of a web app to build the project's knowledge graph. The crawl systematically explores pages, UI states, and navigation flows, then populates the backend's knowledge graph so future evaluations and tests have context about the app.
LOCALHOST SUPPORT: Pass any localhost URL (e.g. http://localhost:3000) and it Just Works. A secure tunnel is automatically created so the remote browser can reach your local dev server.
WHEN TO USE: after a significant new feature, a new environment, or when onboarding a project. NOT for per-change verification — use check_app_in_browser for that.
SCOPE: one crawl per call against one URL. The crawl is long-running (minutes to tens of minutes depending on app size) and populates backend state asynchronously; the tool returns the execution status once the workflow completes. This does NOT return pass/fail — it returns executionId + status + outcome.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL to crawl. Can be any public URL or a localhost/local dev server URL. For localhost URLs, a secure tunnel is automatically created — just make sure your dev server is running on that port. | |
| projectUuid | No | UUID of the project whose knowledge graph the crawl should populate. Auto-detected from the current git repo if omitted. | |
| environmentId | No | UUID of a specific environment to use for the crawl. See available environments in the tool description above. | |
| credentialId | No | UUID of a specific credential for authenticated crawls. See available credentials in the tool description above. | |
| credentialRole | No | Pick a credential by role (e.g. 'admin', 'guest') from the resolved environment. | |
| username | No | A real, existing account email for the target app. Do NOT invent credentials — use one from the available credentials or ask the user. | |
| password | No | The real password for the username above. Do NOT guess. | |
| headless | No | Run the browser in headless mode. Defaults to backend configuration. | |
| timeoutSeconds | No | Maximum wall-time the crawl may run, in seconds (1..1800). Backend enforces this per workflow execution. | |
| repoName | No | GitHub repository name (e.g. 'my-org/my-repo'). Auto-detected from the current git repo — only provide this to run against a different project. |