自然言語のクエリに基づいて京都の寺院をスコア付きで推薦する。旅行者のプロファイル・希望・条件を自由に入力できる。
AI agents call recommend_temples to retrieve information from Akebono MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a retrieval and recommendation tool that queries a database of temple information and returns personalized suggestions. It has no side effects—it does not create, modify, delete, or execute external operations. The worst-case misuse would be receiving irrelevant recommendations, which poses minimal risk. This clearly falls under the Read category.
From the tool's definition Tool provides 'scored and reasoned' recommendations based on 'natural language queries' and retrieves 'detailed temple information'. The description emphasizes recommendation delivery without mentioning data modification, deletion, or command execution.
Attacks that exploit this kind of access
自然言語のクエリに基づいて京都の寺院をスコア付きで推薦する。旅行者のプロファイル・希望・条件を自由に入力できる。. It is categorised as a Read tool in the Akebono MCP MCP Server, which means it retrieves data without modifying state.
Register the Akebono MCP server in PolicyLayer and add a rule for recommend_temples: 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 Akebono MCP. Nothing to install.
recommend_temples 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_temples 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_temples. 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_temples is provided by the Akebono MCP server (yogi-seto/akebono-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 →