페이지/브라우저를 닫고 리소스 해제.
AI agents invoke web_close 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.
This tool closes a browser page or browser instance and releases associated resources. While it doesn't delete persistent data, it terminates an active browser session which is an external operation with real side effects (loss of unsaved browser state, closed tabs). It fits Execute as it triggers an external operation (browser control) rather than a simple read or reversible write.
From the tool's definition 페이지/브라우저를 닫고 리소스 해제 (closes page/browser and releases resources)
Attacks that exploit this kind of access
페이지/브라우저를 닫고 리소스 해제. 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_close: 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_close 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_close 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_close. 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_close 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 →