Query current value of a time series
AI agents call vm_query to retrieve information from Victoriametrics without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries time-series data from VictoriaMetrics to retrieve current values. It performs a read-only operation with no capability to modify, delete, or execute arbitrary logic. The blast radius is minimal: misuse would only expose queried metrics or metrics data that is presumably already monitored. No data is written, deleted, or financial operations are triggered.
From the tool's definition Tool name: vm_query. Description: 'Query current value of a time series' — retrieves data without modification or side effects.
Attacks that exploit this kind of access
Query current value of a time series. It is categorised as a Read tool in the Victoriametrics MCP Server, which means it retrieves data without modifying state.
Register the Victoriametrics MCP server in PolicyLayer and add a rule for vm_query: 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. Nothing to install.
vm_query 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_query 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_query. 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_query is provided by the Victoriametrics 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.
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 →