객체를 이동합니다.
AI agents use object_move 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.
Moving objects in an SVG canvas modifies data (object coordinates/transforms) but does not delete, execute external code, or create irreversible changes. This is a standard Write operation—reversible graphic manipulation. Severity is low because misuse only affects the visual canvas content within this drawing application, with no external side effects, data loss, or system-level impact.
From the tool's definition Tool name 'object_move' and description '객체를 이동합니다' (moves objects) indicates modification of SVG graphic properties. The tool creates or modifies object positions within a canvas/graphics context, which is a reversible operation.
Attacks that exploit this kind of access
객체를 이동합니다. 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 object_move: 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.
object_move 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 object_move 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 object_move. 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.
object_move 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 →