Execute an instant Prometheus query
AI agents invoke instant-query to trigger actions in Prometheus. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a query against an external Prometheus system. While it is primarily read-oriented (retrieving metrics data), it actively executes PromQL expressions against a live datasource rather than passively fetching static data. PromQL can be complex and resource-intensive, and the execution runs against an external system.
From the tool's definition "Execute an instant Prometheus query" — the tool runs a PromQL query against a live Prometheus instance
Attacks that exploit this kind of access
Execute an instant Prometheus query. It is categorised as a Execute tool in the Prometheus MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Prometheus MCP server in PolicyLayer and add a rule for instant-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 Prometheus. Nothing to install.
instant-query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the instant-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 instant-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.
instant-query is provided by the Prometheus MCP server (mateusdata/prometheus-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 →