AI agents call list_hosts to retrieve information from Defined without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
List operations retrieve data without side effects. The empty description lowers confidence slightly, but the clear Read-pattern naming (list_*) and context within a network management server where sibling tools explicitly perform write/execute actions (create_*, add_*, block_*) indicates this is a query tool. No data modification, deletion, or code execution is implied.
From the tool's definition Tool name is 'list_hosts' which indicates a retrieval operation. The verb 'list' is a standard Read operation pattern. Description is empty, but naming convention strongly suggests querying/enumerating hosts without modification.
Attacks that exploit this kind of access
list_hosts. It is categorised as a Read tool in the Defined MCP Server, which means it retrieves data without modifying state.
Register the Defined MCP server in PolicyLayer and add a rule for list_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 Defined. Nothing to install.
list_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_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_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_hosts is provided by the Defined MCP server (quickvm/defined-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 →