도넛 차트를 생성합니다.
AI agents use chart_donut to create or update resources in SVG Canvas MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SVG Canvas MCP environment.
The tool creates new graphical content (a donut chart) within the SVG canvas system. This is a reversible, non-destructive Write operation—the chart can be modified, deleted, or regenerated without permanent consequences. It does not execute arbitrary code, delete data, or trigger financial operations. Severity is low because misuse results only in unwanted visual elements that can be easily undone.
From the tool's definition Tool name 'chart_donut' and description indicate it generates/creates a donut chart (Korean: '도넛 차트를 생성합니다' = 'Generates a donut chart'). This is a creation operation within the SVG canvas context.
Attacks that exploit this kind of access
도넛 차트를 생성합니다. It is categorised as a Write tool in the SVG Canvas MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SVG Canvas MCP server in PolicyLayer and add a rule for chart_donut: 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.
chart_donut is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the chart_donut 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 chart_donut. 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.
chart_donut 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 →