AI agents call ai_metrics to retrieve information from DBJavaGenix without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves internal telemetry/monitoring data about AI service performance. It has no side effects, does not modify state, and does not trigger external operations. It is purely observational and diagnostic in nature, making it a Read operation with low severity.
From the tool's definition Tool returns accumulated AI call metrics (Prompt Caching hit rate, token consumption, error counts) - the description explicitly states 'returns' (返回) metrics without modification. No create, delete, execute, or financial operations.
Documented attack patterns abuse exactly the kind of access ai_metrics gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and DBJavaGenix, and nothing reaches the server without passing your rules. This is the rule we recommend for ai_metrics:
{
"version": "1",
"default": "deny",
"tools": {
"ai_metrics": {}
}
}ai_metrics is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
返回进程内累积的 AI 调用指标 (Prompt Caching 命中率、token 消耗、错误次数)。. It is categorised as a Read tool in the DBJavaGenix MCP Server, which means it retrieves data without modifying state.
Register the DBJavaGenix MCP server in PolicyLayer and add a rule for ai_metrics: 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 DBJavaGenix. Nothing to install.
ai_metrics 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 ai_metrics 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 ai_metrics. 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.
ai_metrics is provided by the DBJavaGenix MCP server (zhaoxingpeng/dbjavagenix). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 33 DBJavaGenix tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
33 DBJavaGenix tools catalogued and risk-classified — across an index of 42,500+ MCP servers.