AI agents invoke xhs_generate_cover to trigger actions in XHS-MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an external operation (image generation) based on input arguments. It is not a simple read/write of existing data, but rather executes a generation process. It could also be considered Write since it creates an image artifact, but the generative/computational execution aspect and its dependency on external browser automation make Execute the most appropriate category.
From the tool's definition 为指定的笔记生成发布需要的封面图片 — generates cover images required for publishing a note, triggering an external image generation operation
Attacks that exploit this kind of access
为指定的笔记生成发布需要的封面图片. It is categorised as a Execute tool in the XHS-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the XHS- MCP server in PolicyLayer and add a rule for xhs_generate_cover: 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 XHS-MCP. Nothing to install.
xhs_generate_cover is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the xhs_generate_cover 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 xhs_generate_cover. 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.
xhs_generate_cover is provided by the XHS- MCP server (lastkimi/xhs-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 →