캔버스의 모든 객체 목록을 조회합니다.
AI agents call object_list 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.
This tool retrieves or queries data about objects on the canvas with no side effects—a classic Read operation. The description explicitly indicates data retrieval ('조회합니다' = 'retrieves/queries') without creating, modifying, or deleting any data. Severity is low because the blast radius of misuse is minimal: an AI agent can only view canvas contents, not alter them.
From the tool's definition Tool name 'object_list' and description indicating it 'retrieves/queries' (조회 = retrieves/queries) all objects on the canvas without modification capability.
Attacks that exploit this kind of access
캔버스의 모든 객체 목록을 조회합니다. 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 object_list: 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_list 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 object_list 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_list. 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_list 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 →