AI agents call vm_labels to retrieve information from VictoriaMetrics-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 label names from VictoriaMetrics, a read-only query operation with no side effects. It does not modify, delete, or execute operations—it only fetches existing data. The blast radius of misuse is minimal: an agent could retrieve metric label information but cannot cause data loss, financial impact, or execute arbitrary code. Low severity reflects the informational nature of the operation.
From the tool's definition Tool name 'vm_labels' and description 'Get all unique label names' indicate a retrieval operation that queries metadata without modifying data.
Documented attack patterns abuse exactly the kind of access vm_labels gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and VictoriaMetrics-mcp-server, and nothing reaches the server without passing your rules. This is the rule we recommend for vm_labels:
{
"version": "1",
"default": "deny",
"tools": {
"vm_labels": {}
}
} vm_labels 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 all unique label names. It is categorised as a Read tool in the VictoriaMetrics-mcp-server MCP Server, which means it retrieves data without modifying state.
Register the VictoriaMetrics-mcp-server MCP server in PolicyLayer and add a rule for vm_labels: 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 VictoriaMetrics-mcp-server. Nothing to install.
vm_labels 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 vm_labels 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 vm_labels. 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.
vm_labels is provided by the VictoriaMetrics-mcp-server MCP server (yincongcyincong/victoriametrics-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from VictoriaMetrics-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.
6 VictoriaMetrics-mcp-server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.