Click an element on the page. Use ref (e.g.
AI agents invoke browserbeam_click to trigger actions in Browserbeam MCP Server. 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 elements in a browser can trigger arbitrary external operations: form submissions, purchases, deletions, navigation, API calls, etc. The effect depends entirely on what element is clicked, making this an Execute-category action with high blast radius since an AI agent could click destructive or financial action buttons.
From the tool's definition 'Click an element on the page' — triggers browser interaction/action on a live web page
Attacks that exploit this kind of access
Click an element on the page. Use ref (e.g. It is categorised as a Execute tool in the Browserbeam MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Browserbeam MCP Server MCP server in PolicyLayer and add a rule for browserbeam_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 Browserbeam MCP Server. Nothing to install.
browserbeam_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 browserbeam_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 browserbeam_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.
browserbeam_click is provided by the Browserbeam MCP Server MCP server (nyku/browserbeam-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →