multi_click · Atlas Browser MCP: Risk & Policy

WHAT IT DOES

What multi_click does on Atlas Browser

AI agents invoke multi_click to trigger actions in Atlas Browser. 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.

WHY IT NEEDS A POLICY

Why multi_click needs a policy

Clicking multiple UI elements is an Execute-category action because it triggers external operations (form submissions, navigation, CAPTCHA solving, checkbox state changes) whose effects are entirely argument-dependent. The CAPTCHA-solving use case is particularly notable as it can bypass security controls.

From the tool's definition 'Click multiple elements at once (useful for CAPTCHA, checkboxes, etc.)' — triggers multiple browser interaction actions that cause external side effects depending on which elements are targeted

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

multi_click Rate-limited

multi_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "multi_click": {
      "limits": [
        {
          "counter": "multi_click_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Atlas Browser, so you can run agents against it safely.

FAQ

Questions about multi_click

What does the multi_click tool do? +

Click multiple elements at once (useful for CAPTCHA, checkboxes, etc.). It is categorised as a Execute tool in the Atlas Browser MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on multi_click? +

Register the Atlas Browser MCP server in PolicyLayer and add a rule for multi_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 Atlas Browser. Nothing to install.

What risk level is multi_click? +

multi_click is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit multi_click? +

Yes. Add a rate_limit block to the multi_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.

How do I block multi_click completely? +

Set action: deny in the PolicyLayer policy for multi_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.

What MCP server provides multi_click? +

multi_click is provided by the Atlas Browser MCP server (lingtravel/atlas-browser). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.