AI agents call grafana_query_panel to retrieve information from Homelab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves monitoring metrics and time-series data from Grafana dashboards. While it is read-only (no side effects), the severity is medium rather than low because the retrieved data could be sensitive infrastructure metrics (CPU usage, memory, network traffic, application performance) from a homelab environment.
From the tool's definition Tool description states it 'Query[s] the actual data values' and 'Returns the last N data points' from Grafana panels. The verb 'query' combined with 'returns data' indicates data retrieval without modification.
Attacks that exploit this kind of access
Query the actual data values from a specific Grafana dashboard panel. Returns the last N data points. Use grafana_get_dashboard first to find the panel_id. It is categorised as a Read tool in the Homelab MCP Server, which means it retrieves data without modifying state.
Register the Homelab MCP server in PolicyLayer and add a rule for grafana_query_panel: 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 Homelab. Nothing to install.
grafana_query_panel 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 grafana_query_panel 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 grafana_query_panel. 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.
grafana_query_panel is provided by the Homelab MCP server (nainounen/homelab-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 →