查询使用率最高的前N名用户
AI agents call query_top_users to retrieve information from Claude Stats MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing usage statistics about top users without modifying, deleting, or executing operations. It is a straightforward read operation with no side effects. The severity is low because the blast radius of misuse—retrieving usage statistics—poses minimal risk compared to other categories.
From the tool's definition Tool name 'query_top_users' and description '查询使用率最高的前N名用户' (query top N users by usage rate) indicates a retrieval operation. The context confirms this is part of a statistical analysis server for querying usage data and generating reports.
Attacks that exploit this kind of access
查询使用率最高的前N名用户. It is categorised as a Read tool in the Claude Stats MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Stats MCP server in PolicyLayer and add a rule for query_top_users: 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 Claude Stats MCP. Nothing to install.
query_top_users 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 query_top_users 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 query_top_users. 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.
query_top_users is provided by the Claude Stats MCP server (upjiang/ai-mcp-study). 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 →