AI agents call grafana_get_dashboard 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 only queries and retrieves information about Grafana dashboard structure (panel IDs, types, titles). It performs a read-only operation with no capability to modify, delete, or execute actions. The blast radius of misuse is minimal—an agent could only access existing monitoring dashboard metadata, which poses no security risk in a homelab context.
From the tool's definition Tool name 'grafana_get_dashboard' and description 'Get the panel list for a Grafana dashboard by UID. Returns panel IDs, types, and titles.' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get the panel list for a Grafana dashboard by UID. Returns panel IDs, types, and titles. 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_get_dashboard: 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_get_dashboard 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_get_dashboard 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_get_dashboard. 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_get_dashboard 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 →