URL 을 헤드리스 브라우저로 엽니다 (K님 화면에 안 뜸).
AI agents invoke web_open 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.
Opening a URL in a headless browser is an execution action that triggers external operations (network requests, potential script execution on the target page). It is not a simple read since it actively launches a browser process and navigates to an arbitrary URL, which could be misused to interact with web services, trigger downloads, or execute web-based actions.
From the tool's definition 'URL 을 헤드리스 브라우저로 엽니다' — opens a URL in a headless browser, triggering an external browser operation
Attacks that exploit this kind of access
URL 을 헤드리스 브라우저로 엽니다 (K님 화면에 안 뜸). 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_open: 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_open 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_open 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_open. 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_open 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 →