获取推荐的图像尺寸列表
AI agents call get_supported_sizes to retrieve information from Zhipu AI Image Generation MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries configuration metadata (supported image sizes) from the Zhipu AI service. It is a read-only operation with no side effects, posing minimal security risk. Classification as Read is appropriate.
From the tool's definition Tool name 'get_supported_sizes' and description indicate retrieval of a static list of supported image dimensions. No data creation, modification, deletion, code execution, or financial operations occur.
Attacks that exploit this kind of access
获取推荐的图像尺寸列表. It is categorised as a Read tool in the Zhipu AI Image Generation MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Zhipu AI Image Generation MCP Server MCP server in PolicyLayer and add a rule for get_supported_sizes: 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 Zhipu AI Image Generation MCP Server. Nothing to install.
get_supported_sizes 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 get_supported_sizes 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 get_supported_sizes. 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.
get_supported_sizes is provided by the Zhipu AI Image Generation MCP Server MCP server (nanguangchou/zhipu_image_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 →