SEMANTIC CLICK: Click an element by its semantic ID. This is the high-level equivalent of Playwright\
AI agents invoke click_element to trigger actions in Scenic MCP. 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 an element triggers external operations in the Scenic application (button presses, navigation, form submissions, etc.). The effect depends on which element is clicked, making it an Execute-category action. Misuse could trigger unintended application flows, but effects are generally not irreversible on their own.
From the tool's definition 'Click an element by its semantic ID' and 'high-level equivalent of Playwright' — triggers a UI interaction/browser action on a running application
Documented attack patterns abuse exactly the kind of access click_element gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Scenic MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for click_element:
{
"version": "1",
"default": "deny",
"tools": {
"click_element": {
"limits": [
{
"counter": "click_element_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}click_element 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.
SEMANTIC CLICK: Click an element by its semantic ID. This is the high-level equivalent of Playwright\. It is categorised as a Execute tool in the Scenic MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Scenic MCP server in PolicyLayer and add a rule for click_element: 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 Scenic MCP. Nothing to install.
click_element 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 click_element 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 click_element. 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.
click_element is provided by the Scenic MCP server (scenic-contrib/scenic_mcp_experimental). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Scenic MCP, 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.
10 Scenic MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.