List Alertmanager alerts through Grafana's Alertmanager datasource proxy.
AI agents call list_alertmanager_alerts to retrieve information from Mcp Grafana without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries alert data from Alertmanager through Grafana without any ability to modify, delete, or trigger alerts. It is a passive read operation with no side effects. The read-only nature of the parent server and the explicit 'list' action confirm this classification.
From the tool's definition Tool name contains 'list' verb and description explicitly states 'List Alertmanager alerts'. The server is described as 'read-only diagnostics' with no mention of alert modification, deletion, or triggering capabilities.
Attacks that exploit this kind of access
List Alertmanager alerts through Grafana's Alertmanager datasource proxy. It is categorised as a Read tool in the Mcp Grafana MCP Server, which means it retrieves data without modifying state.
Register the Mcp Grafana MCP server in PolicyLayer and add a rule for list_alertmanager_alerts: 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 Grafana. Nothing to install.
list_alertmanager_alerts 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 list_alertmanager_alerts 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 list_alertmanager_alerts. 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.
list_alertmanager_alerts is provided by the Mcp Grafana MCP server (romaine-life/mcp-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 →