get_ruler_rules
AI agents call get_ruler_rules 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 'get_' prefix and the server's explicit read-only default stance indicate this tool retrieves Grafana ruler rules without modification. Although the description is empty, the naming pattern and server design make it unlikely this performs mutations. Low severity because reading monitoring rules poses minimal immediate risk to system integrity.
From the tool's definition Tool name 'get_ruler_rules' follows a 'get_' pattern consistent with read-only retrieval. Server is described as providing 'read-only access by default.' No description provided, but naming convention and server context strongly indicate query/retrieval.
Attacks that exploit this kind of access
get_ruler_rules. 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 get_ruler_rules: 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.
get_ruler_rules 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 get_ruler_rules 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 get_ruler_rules. 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.
get_ruler_rules 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 →