先以 get_spots_filtered 在 DB 依城市與人氣取樣；排除 avoid_styles 命中者；
AI agents call recommend_itinerary_candidates to retrieve information from Gogo Backend without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters travel destination data from a PostgreSQL database based on input parameters (city, popularity, style preferences). It performs no modifications, deletions, financial operations, or code execution—purely data retrieval and filtering operations typical of Read category.
From the tool's definition Tool description indicates sampling from DB by city and popularity, filtering based on avoid_styles. No mention of CREATE, UPDATE, DELETE, or external execution.
Attacks that exploit this kind of access
先以 get_spots_filtered 在 DB 依城市與人氣取樣；排除 avoid_styles 命中者；. It is categorised as a Read tool in the Gogo Backend MCP Server, which means it retrieves data without modifying state.
Register the Gogo Backend MCP server in PolicyLayer and add a rule for recommend_itinerary_candidates: 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 Gogo Backend. Nothing to install.
recommend_itinerary_candidates 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 recommend_itinerary_candidates 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 recommend_itinerary_candidates. 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.
recommend_itinerary_candidates is provided by the Gogo Backend MCP server (jjjtyy666/gogo-backend-mcp6). 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 →