生成微信小程序上线前检查清单，包含云开发、隐私、审核、客户私密相册交付。
AI agents call miniapp_launch_checklist to retrieve information from Wechat Miniapp Engineering without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool generates a checklist (a read/advisory output) covering cloud development, privacy, review, and delivery topics. It produces informational content for the developer to act on, with no indication it executes, modifies, or deletes anything itself. Severity is low as misuse would at most produce an incorrect or misleading checklist.
From the tool's definition 生成微信小程序上线前检查清单 (Generate pre-launch checklist) — generates/reads a checklist document
Attacks that exploit this kind of access
生成微信小程序上线前检查清单，包含云开发、隐私、审核、客户私密相册交付。. It is categorised as a Read tool in the Wechat Miniapp Engineering MCP Server, which means it retrieves data without modifying state.
Register the Wechat Miniapp Engineering MCP server in PolicyLayer and add a rule for miniapp_launch_checklist: 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 Wechat Miniapp Engineering. Nothing to install.
miniapp_launch_checklist 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 miniapp_launch_checklist 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 miniapp_launch_checklist. 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.
miniapp_launch_checklist is provided by the Wechat Miniapp Engineering MCP server (lychee20000105/wechat-miniapp-engineering-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 →