AI agents invoke browser_click to trigger actions in Abrasio. 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 a browser element is an external operation whose effects are entirely argument-dependent. A click could submit a form, confirm a deletion, initiate a financial transaction, or navigate to a new page. Since the blast radius depends on what is clicked, Execute is the appropriate category (with Financial or Destructive possible depending on context).
From the tool's definition 'Click an element using a CSS selector' — triggers a real browser click action on a live webpage, which can submit forms, trigger purchases, confirm dialogs, or initiate any web-based operation depending on the element clicked.
Attacks that exploit this kind of access
Click an element using a CSS selector. It is categorised as a Execute tool in the Abrasio MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Abrasio MCP server in PolicyLayer and add a rule for browser_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 Abrasio. Nothing to install.
browser_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 browser_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 browser_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.
browser_click is provided by the Abrasio MCP server (scrape-technology/abrasio-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 →