根据省份名称获取该省所有景点数据（从本地JSON文件读取）
AI agents call get_spots_by_province to retrieve information from Chinese Tourism Spots MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns data (scenic spots) from a local data source without creating, modifying, deleting, or executing operations. It is a pure data retrieval function with no side effects, fitting the Read category. Severity is low since reading scenic spot data poses minimal risk even if misused by an AI agent.
From the tool's definition Tool retrieves scenic spot data by province name from local JSON file. Description uses "获取" (retrieve/get) which indicates a read operation with no modifications or side effects.
Attacks that exploit this kind of access
根据省份名称获取该省所有景点数据（从本地JSON文件读取）. It is categorised as a Read tool in the Chinese Tourism Spots MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Chinese Tourism Spots MCP Server MCP server in PolicyLayer and add a rule for get_spots_by_province: 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 Chinese Tourism Spots MCP Server. Nothing to install.
get_spots_by_province 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 get_spots_by_province 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 get_spots_by_province. 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.
get_spots_by_province is provided by the Chinese Tourism Spots MCP Server MCP server (sekusrevo/mcpproject). 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 →