Get information about targets
AI agents call get-targets to retrieve information from Prometheus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about Prometheus targets (monitored systems/endpoints) without side effects. It aligns with the Read category pattern of discovery and information retrieval tools (similar to sibling tools like get-metadata, get-status, get-series).
From the tool's definition Tool name 'get-targets' and description 'Get information about targets' indicate a retrieval operation. The server context confirms this is part of Prometheus metrics interaction, where targets refer to monitored endpoints.
Attacks that exploit this kind of access
Get information about targets. It is categorised as a Read tool in the Prometheus MCP Server, which means it retrieves data without modifying state.
Register the Prometheus MCP server in PolicyLayer and add a rule for get-targets: 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 Prometheus. Nothing to install.
get-targets 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-targets 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-targets. 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-targets is provided by the Prometheus MCP server (mateusdata/prometheus-mcp-server). 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 →