explore_query
AI agents call explore_query 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 'explore_query' indicates a read operation that retrieves or queries data without side effects. Although the description is empty, the server's stated read-only default access and the absence of destructive/write keywords strongly suggest this is a safe read operation.
From the tool's definition Tool name 'explore_query' suggests a querying/exploration operation typical of read-only data retrieval. Server description explicitly states 'provides read-only access by default.' No mutation keywords (create, update, delete, modify) in the tool name.
Attacks that exploit this kind of access
explore_query. 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 explore_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 Mcp Read Only Grafana. Nothing to install.
explore_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 explore_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 explore_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.
explore_query 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 →