Runs Playwright tests with JSON reporter and returns structured results with pass/fail status, duration, and error messages.
AI agents invoke playwright to trigger actions in Http. 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.
Playwright tests can perform arbitrary browser actions including navigation, form submission, file uploads, API calls, and DOM manipulation. The tool executes external operations whose effects depend on the test scripts being run, making it Execute category. Severity is high because a misused agent could trigger broad side effects through browser automation.
From the tool's definition 'Runs Playwright tests' — executes browser automation test scripts whose effects depend entirely on the test content and arguments provided
Documented attack patterns abuse exactly the kind of access playwright gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Http, and nothing reaches the server without passing your rules. This is the rule we recommend for playwright:
{
"version": "1",
"default": "deny",
"tools": {
"playwright": {
"limits": [
{
"counter": "playwright_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}playwright 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.
Runs Playwright tests with JSON reporter and returns structured results with pass/fail status, duration, and error messages. It is categorised as a Execute tool in the Http MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Http MCP server in PolicyLayer and add a rule for playwright: 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 Http. Nothing to install.
playwright 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 playwright 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 playwright. 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.
playwright is provided by the Http MCP server (@paretools/http). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Http, 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.
202 Http tools catalogued and risk-classified — across an index of 43,000+ MCP servers.