파이 차트를 생성합니다.
AI agents use chart_pie 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 generates/creates visual content (a pie chart) within the SVG canvas, which is a write operation that adds or modifies the drawing. It does not read existing data, execute arbitrary code, delete anything, or involve financial operations. The blast radius of misuse is minimal—at worst an agent creates unwanted chart graphics that can be easily undone via standard undo/editing operations.
From the tool's definition Tool creates a pie chart graphic ('파이 차트를 생성합니다' translates to 'Creates a pie chart'). This is a data visualization creation action that modifies the canvas by adding a new graphic element.
Attacks that exploit this kind of access
파이 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_pie: 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_pie 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_pie 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_pie. 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_pie 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 →