Click a target by text using the canonical fallback chain: AX → CDP → OCR. Automatically retries and falls through methods.
AI agents invoke click_with_fallback to trigger actions in ScreenHand. 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 performs UI click actions on desktop or browser elements using multiple input methods (Accessibility APIs, Chrome DevTools Protocol, OCR). Clicking UI elements triggers external operations whose effects depend entirely on what is clicked — could submit forms, trigger purchases, delete data, navigate pages, or launch processes.
From the tool's definition 'Click a target by text using the canonical fallback chain: AX → CDP → OCR. Automatically retries and falls through methods.'
Documented attack patterns abuse exactly the kind of access click_with_fallback gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ScreenHand, and nothing reaches the server without passing your rules. This is the rule we recommend for click_with_fallback:
{
"version": "1",
"default": "deny",
"tools": {
"click_with_fallback": {
"limits": [
{
"counter": "click_with_fallback_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}click_with_fallback 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 a target by text using the canonical fallback chain: AX → CDP → OCR. Automatically retries and falls through methods. It is categorised as a Execute tool in the ScreenHand MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ScreenHand MCP server in PolicyLayer and add a rule for click_with_fallback: 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 ScreenHand. Nothing to install.
click_with_fallback 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_with_fallback 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_with_fallback. 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_with_fallback is provided by the ScreenHand MCP server (manushi4/screenhand). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ScreenHand, 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.
89 ScreenHand tools catalogued and risk-classified — across an index of 43,000+ MCP servers.