AI agents call search_hosts to retrieve information from Homelab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs searching and filtering operations on host data within the Ansible inventory (likely), retrieving information based on search criteria. Search operations are inherently read-only with no side effects, making this a Read category tool. The low severity reflects that querying inventory data poses minimal risk even if an AI agent misuses it—it cannot modify infrastructure or execute commands.
From the tool's definition Tool name 'search_hosts' and description 'Search for hosts by name pattern or by variable values' indicates a query/search operation with no modification or execution of commands.
Attacks that exploit this kind of access
Search for hosts by name pattern or by variable values. It is categorised as a Read tool in the Homelab MCP Server, which means it retrieves data without modifying state.
Register the Homelab MCP server in PolicyLayer and add a rule for search_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 Homelab. Nothing to install.
search_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 search_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 search_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.
search_hosts is provided by the Homelab MCP server (myraffy/homelab-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 →