融合 CodeGraph 的 4-tier context 思路，按任务输出 Core/Near/Extended/Background 四层小程序工程上下文。
AI agents call miniapp_relevant_context 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 retrieves and presents contextual information about WeChat Mini Program projects in a structured format. It performs analysis and context aggregation without side effects—no data is created, modified, deleted, or executed. This is a pure read operation that helps developers understand code structure and relationships.
From the tool's definition The tool 'miniapp_relevant_context' outputs context information organized in tiers (Core/Near/Extended/Background) based on tasks.
Attacks that exploit this kind of access
融合 CodeGraph 的 4-tier context 思路，按任务输出 Core/Near/Extended/Background 四层小程序工程上下文。. 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_relevant_context: 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_relevant_context 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_relevant_context 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_relevant_context. 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_relevant_context 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 →