AI agents invoke testkit_run to trigger actions in Yaver. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
only | string | — | Only run a single spec by name |
root | string | — | Spec root (default: yaver-tests) |
video | boolean | — | Force screencast capture for every spec (overrides per-spec artifacts.video). Frames flush to the run's artifact dir on both pass + fail so the workspace clip p |
headful | boolean | — | Show the browser visibly |
retries | integer | — | Flake retries (default 0) |
concurrency | integer | — | Parallel workers (default 1) |
Parameters from the server's own tool schema.
testkit_run triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
Run the yaver-test-sdk specs end-to-end on the dev's machine via the embedded chromedp runner. Returns suite results inline. Use this to drive a 'fix → test → fix' loop without spawning Playwright. It is categorised as a Execute tool in the Yaver MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
testkit_run accepts 6 parameters: only, root, video, headful, retries, concurrency. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for testkit_run: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Yaver. Nothing to install.
testkit_run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the testkit_run rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for testkit_run. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
testkit_run is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.