Click left mouse button
AI agents invoke browser_screen_click to trigger actions in Playwright MCP with Electron Support. 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.
Clicking in a browser or desktop application is an Execute-level action because it triggers external operations whose effects depend on the target element — it could submit forms, navigate pages, execute JavaScript handlers, or perform any application-level action. The blast radius is high because a misused click could trigger irreversible actions (e.g., confirm deletion, submit payment) depending on context.
From the tool's definition 'Click left mouse button' — triggers a UI interaction (mouse click) in a browser or Electron desktop application, which can activate buttons, links, forms, and arbitrary application logic depending on where the click is directed.
Documented attack patterns abuse exactly the kind of access browser_screen_click gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright MCP with Electron Support, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_screen_click:
{
"version": "1",
"default": "deny",
"tools": {
"browser_screen_click": {
"limits": [
{
"counter": "browser_screen_click_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}browser_screen_click 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.
Click left mouse button. It is categorised as a Execute tool in the Playwright MCP with Electron Support MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Playwright MCP with Electron Support MCP server in PolicyLayer and add a rule for browser_screen_click: 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 Playwright MCP with Electron Support. Nothing to install.
browser_screen_click 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_screen_click 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_screen_click. 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_screen_click is provided by the Playwright MCP with Electron Support MCP server (robertn702/playwright-mcp-electron). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Playwright MCP with Electron Support, 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.
34 Playwright MCP with Electron Support tools catalogued and risk-classified — across an index of 43,000+ MCP servers.