selector 또는 role+name 으로 요소 클릭.
AI agents invoke web_click to trigger actions in K-Personal MCP. 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 web elements can trigger arbitrary actions in a browser context (form submissions, purchases, navigation, deletions), making this an Execute-level tool with high severity due to unpredictable side effects depending on what element is clicked.
From the tool's definition web_click — clicks elements in a headless browser via selector or role+name; triggers external operations whose effects depend on arguments
Attacks that exploit this kind of access
selector 또는 role+name 으로 요소 클릭. It is categorised as a Execute tool in the K-Personal MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the K-Personal MCP server in PolicyLayer and add a rule for web_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 K-Personal MCP. Nothing to install.
web_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 web_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 web_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.
web_click is provided by the K-Personal MCP server (lee30934-byte/k-personal-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 →