AI agents call prometheus_range_query to retrieve information from Homelab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and retrieves historical monitoring data from Prometheus. It has no side effects, cannot modify infrastructure, delete data, execute code, or commit financial transactions. The read-only nature of PromQL range queries and the stated use case of 'trend analysis' confirm this is a pure data retrieval operation.
From the tool's definition Tool description explicitly states 'Run a PromQL range query to get historical metric values' and is described as 'Useful for trend analysis'. PromQL queries are read-only operations that retrieve and aggregate time-series data without modification.
Attacks that exploit this kind of access
Run a PromQL range query to get historical metric values over time. Useful for trend analysis (e.g. CPU over last 24h). It is categorised as a Read tool in the Homelab MCP Server, which means it retrieves data without modifying state.
Register the Homelab MCP server in PolicyLayer and add a rule for prometheus_range_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 Homelab. Nothing to install.
prometheus_range_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 prometheus_range_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 prometheus_range_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.
prometheus_range_query is provided by the Homelab MCP server (nainounen/homelab-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 →