객체를 ID로 선택하고 정보를 조회합니다.
AI agents call object_select 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.
The tool selects an object by ID and retrieves its information. This is a read/query operation with no side effects. The description translates from Korean as 'Select an object by ID and query its information.' No data is modified or created.
From the tool's definition 객체를 ID로 선택하고 정보를 조회합니다 — 'retrieves/queries information about an object by ID'
Attacks that exploit this kind of access
객체를 ID로 선택하고 정보를 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_select: 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_select 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_select 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_select. 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_select 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 →