AI agents call liara_get_metrics to retrieve information from Liara 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 monitoring metrics from deployed applications—a pure read operation that queries existing data without creating, modifying, deleting, or executing any infrastructure changes. The severity is low because metrics are typically non-sensitive operational data, and retrieval poses minimal risk even if accessed inappropriately.
From the tool's definition Tool name 'liara_get_metrics' with description 'Get app metrics summary' indicates a retrieval operation with no side effects. The verb 'Get' and context of fetching metrics (read-only monitoring data) confirms this is a data query operation.
Documented attack patterns abuse exactly the kind of access liara_get_metrics gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Liara MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for liara_get_metrics:
{
"version": "1",
"default": "deny",
"tools": {
"liara_get_metrics": {}
}
}liara_get_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.
Get app metrics summary. It is categorised as a Read tool in the Liara MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Liara MCP Server MCP server in PolicyLayer and add a rule for liara_get_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 Liara MCP Server. Nothing to install.
liara_get_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 liara_get_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 liara_get_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.
liara_get_metrics is provided by the Liara MCP Server MCP server (razavioo/liara-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Liara MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
108 Liara MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.