生成AI图片
AI agents use create_image to create or update resources in LiblibAI Picture Generator — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LiblibAI Picture Generator environment.
This tool creates new image artifacts through an AI generation service. While not destructive or financial in direct terms, it consumes account credits (reversible but with cost implications) and generates persistent digital content. The primary action is creation (Write category), not merely retrieval.
From the tool's definition Tool name 'create_image' and description '生成AI图片' (generate AI image) indicates creation of new digital content.
Attacks that exploit this kind of access
生成AI图片. It is categorised as a Write tool in the LiblibAI Picture Generator MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LiblibAI Picture Generator MCP server in PolicyLayer and add a rule for create_image: 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 LiblibAI Picture Generator. Nothing to install.
create_image 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 create_image 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 create_image. 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.
create_image is provided by the LiblibAI Picture Generator MCP server (nathansnmmer/picture). 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 →