기존 SVG 파일을 엽니다.
AI agents call svg_open to retrieve information from SVG Canvas MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Opening a file is a read operation — it loads existing SVG content into the canvas without modifying or deleting it. The description explicitly references opening an existing file, implying retrieval/loading. Severity is low as misuse would only expose SVG file contents.
From the tool's definition Tool name 'svg_open' and description '기존 SVG 파일을 엽니다' (meaning 'Open an existing SVG file')
Attacks that exploit this kind of access
기존 SVG 파일을 엽니다. It is categorised as a Read tool in the SVG Canvas MCP MCP Server, which means it retrieves data without modifying state.
Register the SVG Canvas MCP server in PolicyLayer and add a rule for svg_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 SVG Canvas MCP. Nothing to install.
svg_open is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the svg_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 svg_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.
svg_open 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 →