Perform a double click at the specified coordinates.
AI agents invoke double_click to trigger actions in Computer Use. 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.
Double-clicking is a browser/desktop UI action whose effects are entirely dependent on the target coordinates. It can open executable files, launch applications, confirm dialogs, or trigger other system-level operations. This falls under Execute as it performs external operations with argument-dependent effects.
From the tool's definition "Perform a double click at the specified coordinates" — triggers a UI interaction (double-click) on the computer, which can open files, launch applications, or activate controls depending on where it is clicked.
Documented attack patterns abuse exactly the kind of access double_click gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Computer Use, and nothing reaches the server without passing your rules. This is the rule we recommend for double_click:
{
"version": "1",
"default": "deny",
"tools": {
"double_click": {
"limits": [
{
"counter": "double_click_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}double_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.
Perform a double click at the specified coordinates. It is categorised as a Execute tool in the Computer Use MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Computer Use MCP server in PolicyLayer and add a rule for double_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 Computer Use. Nothing to install.
double_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 double_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 double_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.
double_click is provided by the Computer Use MCP server (spencerkinney/computer-use-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Computer Use, 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.
15 Computer Use tools catalogued and risk-classified — across an index of 43,000+ MCP servers.