按 dimension 切片回傳勞動爭議判例聚合統計。每個 cell 含案件數、p25/中位/p75 金額、平均月薪(勝訴率試用版暫略)。
AI agents call case_stats to retrieve information from SinoVerdict MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes pre-existing structured data from a judgment corpus without creating, modifying, deleting, or executing external operations. It performs read-only statistical aggregation and slicing operations. The low severity reflects minimal risk: the data returned is aggregate-level statistics, not sensitive individual case details, and there are no side effects from querying.
From the tool's definition Tool returns aggregated statistics (案件數、金額、平均月薪) sliced by dimensions from a corpus of labor dispute judgments.
Attacks that exploit this kind of access
按 dimension 切片回傳勞動爭議判例聚合統計。每個 cell 含案件數、p25/中位/p75 金額、平均月薪(勝訴率試用版暫略)。. It is categorised as a Read tool in the SinoVerdict MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SinoVerdict MCP Server MCP server in PolicyLayer and add a rule for case_stats: 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 SinoVerdict MCP Server. Nothing to install.
case_stats 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 case_stats 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 case_stats. 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.
case_stats is provided by the SinoVerdict MCP Server MCP server (jack0752168/wenshucha-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 →