AI agents call self_test to retrieve information from Grafana without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The self_test tool only retrieves diagnostic information about server status and connectivity. It has no side effects, creates no data modifications, executes no external commands, and poses minimal risk. This is a pure Read operation focused on health monitoring.
From the tool's definition Tool performs health check operations: 'Check MCP server health: Grafana connectivity, version, and selected auth method.' These are diagnostic read-only operations that query status without modifying data or triggering external actions.
Attacks that exploit this kind of access
Check MCP server health: Grafana connectivity, version, and selected auth method. It is categorised as a Read tool in the Grafana MCP Server, which means it retrieves data without modifying state.
Register the Grafana MCP server in PolicyLayer and add a rule for self_test: 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. Nothing to install.
self_test 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 self_test 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 self_test. 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.
self_test is provided by the Grafana MCP server (ninanung/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 →