查询埋点事件的所有字段定义，返回字段类型、说明、枚举值等信息
AI agents call query_event_fields 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 metadata about event tracking schema (field definitions, types, descriptions, enums). It is a read-only query operation that does not create, modify, delete, or execute any operations. The blast radius of misuse is minimal—an agent could only retrieve schema documentation that is likely already visible to authorized users. No data modification, code execution, or financial impact is possible.
From the tool's definition Tool name 'query_event_fields' and description '查询埋点事件的所有字段定义，返回字段类型、说明、枚举值等信息' (query tracking event field definitions, returns field type, description, enum values).
Attacks that exploit this kind of access
查询埋点事件的所有字段定义，返回字段类型、说明、枚举值等信息. 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_event_fields: 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_event_fields 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_event_fields 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_event_fields. 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_event_fields 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 →