Browse available Prometheus metrics. Search by name pattern.
AI agents call prom_metrics_explore 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 retrieves and queries available metrics from Prometheus without side effects. It enables discovery and inspection of metric names through search patterns, which is a typical Read operation. The severity is low because even if misused, browsing metric names poses minimal risk to systems or data integrity.
From the tool's definition Tool description states 'Browse available Prometheus metrics' and 'Search by name pattern' — both read-only operations that query metric metadata without modifying data or executing operations.
Attacks that exploit this kind of access
Browse available Prometheus metrics. Search by name pattern. 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_metrics_explore: 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_metrics_explore 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_metrics_explore 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_metrics_explore. 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_metrics_explore 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 →