获取图片生成的最佳实践建议
AI agents call get_generation_tips to retrieve information from Jimeng Image MCP Server 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 guidance/tips data with no side effects. It does not generate, modify, delete, or execute operations—it only returns read-only information to assist users in using image generation features. No blast radius from misuse.
From the tool's definition Tool name 'get_generation_tips' and description '获取图片生成的最佳实践建议' (Get best practice suggestions for image generation) indicates retrieval of informational content about image generation techniques.
Attacks that exploit this kind of access
获取图片生成的最佳实践建议. It is categorised as a Read tool in the Jimeng Image MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Jimeng Image MCP Server MCP server in PolicyLayer and add a rule for get_generation_tips: 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 Jimeng Image MCP Server. Nothing to install.
get_generation_tips 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_generation_tips 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_generation_tips. 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_generation_tips is provided by the Jimeng Image MCP Server MCP server (nanguangchou/jimeng_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 →