입력란에 텍스트를 채웁니다 (기존 값 덮어씀).
AI agents invoke web_fill 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 performs browser automation by filling form fields, overwriting existing content. It triggers external operations in a browser context whose effects depend on arguments. While it modifies data in a form, the action itself is an execution of browser automation that can submit credentials, fill sensitive forms, or interact with web applications — making Execute the most appropriate category.
From the tool's definition '입력란에 텍스트를 채웁니다 (기존 값 덮어씀)' — fills input fields in a browser, overwriting existing values; part of headless browser automation suite
Attacks that exploit this kind of access
입력란에 텍스트를 채웁니다 (기존 값 덮어씀). 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_fill: 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_fill 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_fill 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_fill. 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_fill 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 →