Click on an element identified by its ref ID from the snapshot (e.g.
AI agents invoke cloak_click to trigger actions in CloakBrowser 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 an element in a browser triggers external operations whose effects depend on what is clicked — form submissions, navigation, button actions, purchases, etc. This is a browser interaction/execution action, not a simple read or write to a data store. Severity is medium because the impact depends entirely on the target element, but misuse could trigger significant actions.
From the tool's definition Click on an element identified by its ref ID from the snapshot
Attacks that exploit this kind of access
Click on an element identified by its ref ID from the snapshot (e.g. It is categorised as a Execute tool in the CloakBrowser MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the CloakBrowser MCP Server MCP server in PolicyLayer and add a rule for cloak_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 CloakBrowser MCP Server. Nothing to install.
cloak_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 cloak_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 cloak_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.
cloak_click is provided by the CloakBrowser MCP Server MCP server (miwoomiwoo/cloakbrowser-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 →