현재 캔버스를 브라우저에서 미리봅니다. (Playwright MCP 연동)
AI agents invoke preview_browser to trigger actions in SVG Canvas 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 launches or interacts with a browser to preview the canvas, leveraging Playwright. Since it executes browser automation (an external operation), it falls under Execute. The blast radius is medium as it opens a browser session but does not modify or delete data.
From the tool's definition 브라우저에서 미리봅니다 (Playwright MCP 연동) — triggers an external browser action via Playwright integration
Attacks that exploit this kind of access
현재 캔버스를 브라우저에서 미리봅니다. (Playwright MCP 연동). It is categorised as a Execute tool in the SVG Canvas MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the SVG Canvas MCP server in PolicyLayer and add a rule for preview_browser: 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 SVG Canvas MCP. Nothing to install.
preview_browser 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 preview_browser 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 preview_browser. 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.
preview_browser is provided by the SVG Canvas MCP server (kim62210/svg-canvas-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 →