Execute arbitrary PromQL against a sensor\
AI agents invoke query_sensor_metric to trigger actions in Grafana MCP Server. 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.
The tool executes arbitrary PromQL queries against a sensor data source. While PromQL is typically read-only for metrics retrieval, 'arbitrary' execution of queries against infrastructure can have broad blast radius implications. It falls under Execute as it runs query code dynamically against external systems, with the exact effects depending on the PromQL expression provided.
From the tool's definition Execute arbitrary PromQL against a sensor
Attacks that exploit this kind of access
Execute arbitrary PromQL against a sensor\. It is categorised as a Execute tool in the Grafana MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Grafana MCP Server MCP server in PolicyLayer and add a rule for query_sensor_metric: 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 Grafana MCP Server. Nothing to install.
query_sensor_metric 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 query_sensor_metric 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 query_sensor_metric. 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.
query_sensor_metric is provided by the Grafana MCP Server MCP server (quanticsoul4772/grafana-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 →