list_loki_hosts
AI agents call list_loki_hosts to retrieve information from MCP Prometheus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
List operations retrieve and enumerate data without modification. No indication of side effects, command execution, or data alteration. The tool fits the Read category pattern established by similar sibling tools. Confidence reduced slightly due to empty description, but naming and context are clear indicators.
From the tool's definition Tool name 'list_loki_hosts' indicates a listing operation. Server context describes querying metrics and listing resources (list_checks, list_environments, list_servers patterns).
Attacks that exploit this kind of access
list_loki_hosts. It is categorised as a Read tool in the MCP Prometheus MCP Server, which means it retrieves data without modifying state.
Register the MCP Prometheus MCP server in PolicyLayer and add a rule for list_loki_hosts: 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 Prometheus. Nothing to install.
list_loki_hosts 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_loki_hosts 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_loki_hosts. 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_loki_hosts is provided by the MCP Prometheus MCP server (yeonkyu-git/mcp-prometheus-loki). 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 →