[WRITE] Get the notification policy tree.
AI agents call get_notification_policies 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.
Despite the '[WRITE]' tag in the description, the function 'get_notification_policies' performs a retrieval operation with no side effects. It queries and returns notification policy configuration without modifying, creating, or deleting data. The server itself advertises 'read-only access by default,' and this tool aligns with that design.
From the tool's definition Tool name is 'get_notification_policies' with description '[WRITE] Get the notification policy tree.' The verb 'Get' indicates retrieval of data.
Attacks that exploit this kind of access
[WRITE] Get the notification policy tree. 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_notification_policies: 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_notification_policies 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_notification_policies 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_notification_policies. 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_notification_policies 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 →