取得目前使用者過去3個月的行動網路用量資料，用於分析漫遊需求。系統會自動提供 userId，不需要參數。
AI agents call retrieveUsage to retrieve information from Remote MCP Server (Authless) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves historical mobile data usage information (past 3 months) for a specific user. This is a data retrieval operation with no modifications or irreversible effects. Classified as Read.
From the tool's definition Tool description states it 'retrieve[s]...usage data' (retrieve indicates Read operation). Provides historical mobile network usage for 'analysis', which is data retrieval with no side effects.
Attacks that exploit this kind of access
取得目前使用者過去3個月的行動網路用量資料，用於分析漫遊需求。系統會自動提供 userId，不需要參數。. It is categorised as a Read tool in the Remote MCP Server (Authless) MCP Server, which means it retrieves data without modifying state.
Register the Remote MCP Server (Authless) MCP server in PolicyLayer and add a rule for retrieveUsage: 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 Remote MCP Server (Authless). Nothing to install.
retrieveUsage 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 retrieveUsage 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 retrieveUsage. 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.
retrieveUsage is provided by the Remote MCP Server (Authless) MCP server (yulunjiang/remote-mcp-server-authless). 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 →