Execute a LogQL query against a Loki datasource to search logs
AI agents invoke query_loki 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 runs an active query against a Loki datasource. While primarily read-oriented in intent, it executes arbitrary LogQL queries against an external system, placing it in the Execute category. Misuse could involve crafting queries that cause excessive load or expose sensitive log data at scale.
From the tool's definition Execute a LogQL query against a Loki datasource to search logs
Attacks that exploit this kind of access
Execute a LogQL query against a Loki datasource to search logs. 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_loki: 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_loki 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_loki 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_loki. 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_loki 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 →