解释埋点字段的含义、类型和枚举值
AI agents call explain_field 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 queries documentation or schema information about tracking data fields to provide explanatory information to users. It is purely informational with no side effects, fitting the Read category (retrieves data; no side effects). The low severity reflects minimal blast radius—misuse would only return incorrect or misleading field explanations, not expose sensitive data at scale or enable harmful operations.
From the tool's definition Tool name 'explain_field' and description indicate it retrieves and explains metadata about tracking fields (meaning, type, enum values). No mutation, deletion, or execution of arbitrary operations.
Attacks that exploit this kind of access
解释埋点字段的含义、类型和枚举值. 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 explain_field: 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.
explain_field 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 explain_field 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 explain_field. 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.
explain_field 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 →