借鉴 Understand-Anything 的知识图谱思路，生成本地小程序项目地图：页面、文件、云函数、集合和依赖边。
AI agents call miniapp_project_map 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 is a code analysis and visualization tool that reads and maps project structure without side effects. It inspects the project's architecture to produce documentation/diagrams. No data is modified, deleted, or executed—it purely retrieves and organizes information about the miniapp's components and their relationships.
From the tool's definition Tool generates a project map (页面、文件、云函数、集合和依赖边 - pages, files, cloud functions, collections, and dependency edges) through visualization and analysis of existing project structure.
Attacks that exploit this kind of access
借鉴 Understand-Anything 的知识图谱思路，生成本地小程序项目地图：页面、文件、云函数、集合和依赖边。. 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_project_map: 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_project_map 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_project_map 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_project_map. 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_project_map 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 →