query_loki
AI agents call query_loki to retrieve information from Mcp Read Only Grafana without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'query_loki' implies querying Loki (Grafana's log aggregation system) for log data. The server description emphasizes read-only access by default. However, the description is empty, which reduces confidence. Loki queries can retrieve sensitive log data, making misuse a medium severity concern. The 'query' prefix and server context both point to Read category.
From the tool's definition Tool name 'query_loki' and server described as 'read-only access by default'; 'query' prefix strongly suggests data retrieval from Loki log aggregation system.
Attacks that exploit this kind of access
query_loki. It is categorised as a Read tool in the Mcp Read Only Grafana MCP Server, which means it retrieves data without modifying state.
Register the Mcp Read Only Grafana 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 Mcp Read Only Grafana. Nothing to install.
query_loki 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 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 Mcp Read Only Grafana MCP server (lukleh/mcp-read-only-grafana). 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 →