Run a Playwright test script against the browser inside a VM. Has
AI agents invoke browser_run_test to trigger actions in Taw Computer. 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.
This tool executes Playwright test scripts against a live browser in a VM environment. While tests are typically non-destructive by design, the execution of arbitrary test code falls squarely into the Execute category because: (1) it runs code whose effects depend on the test script content, (2) it can trigger browser interactions with real side effects (navigation, form submission, clicks), and (3) misuse could…
From the tool's definition Tool description states 'Run a Playwright test script' which executes arbitrary test code. Sibling tools (browser_click_ref, browser_type_ref, browser_eval, browser_navigate) confirm this server controls a live browser instance capable of performing actions…
Documented attack patterns abuse exactly the kind of access browser_run_test gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Taw Computer, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_run_test:
{
"version": "1",
"default": "deny",
"tools": {
"browser_run_test": {
"limits": [
{
"counter": "browser_run_test_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}browser_run_test stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Run a Playwright test script against the browser inside a VM. Has. It is categorised as a Execute tool in the Taw Computer MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Taw Computer MCP server in PolicyLayer and add a rule for browser_run_test: 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 Taw Computer. Nothing to install.
browser_run_test 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 browser_run_test 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 browser_run_test. 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.
browser_run_test is provided by the Taw Computer MCP server (tawgroup/taw-computer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Taw Computer, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
36 Taw Computer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.