List all active and pending alerts with severity and annotations.
AI agents call prom_alerts to retrieve information from RedisNexus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and displays alert data from a monitoring system (Prometheus). It performs a read-only query that returns existing alert information without modifying, deleting, or executing anything. The 'List' action is characteristic of Read category tools. Severity is low because exposure of alert data, while potentially informative to an attacker, does not directly compromise systems or data.
From the tool's definition Tool name 'prom_alerts' and description 'List all active and pending alerts' indicate a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
List all active and pending alerts with severity and annotations. It is categorised as a Read tool in the RedisNexus MCP Server, which means it retrieves data without modifying state.
Register the RedisNexus MCP server in PolicyLayer and add a rule for prom_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 RedisNexus. Nothing to install.
prom_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 prom_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 prom_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.
prom_alerts is provided by the RedisNexus MCP server (rajkumar-madhu/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 →