生成小程序页面、文件、路由、云函数、controller、集合之间的 Mermaid 依赖图。
AI agents call miniapp_dependency_diagram 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.
This tool inspects and visualizes project dependencies—a read-only operation that retrieves structural information about a WeChat Mini Program and renders it as a diagram. It performs analysis without modifying state, executing code, or triggering deployments. The output is a diagram representation of dependencies, typical of documentation and architecture visualization tools.
From the tool's definition Tool generates Mermaid dependency diagrams by analyzing relationships between pages, files, routing, cloud functions, controllers, and collections.
Attacks that exploit this kind of access
生成小程序页面、文件、路由、云函数、controller、集合之间的 Mermaid 依赖图。. 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_dependency_diagram: 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_dependency_diagram 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_dependency_diagram 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_dependency_diagram. 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_dependency_diagram 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 →