AI agents call remote_host_inventory to retrieve information from Infra Ops without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about remote hosts and their connectivity without modifying any state, executing code, or triggering external operations. It is a read-only operation comparable to 'list' or 'get' operations. The low severity reflects that an AI agent querying this tool can only discover infrastructure metadata with no destructive or harmful side effects.
From the tool's definition Tool name includes 'List' and 'check' actions; description states 'List configured remote hosts and check their connectivity status', which is a passive inventory query with no data modification or command execution.
Attacks that exploit this kind of access
List configured remote hosts and check their connectivity status. It is categorised as a Read tool in the Infra Ops MCP Server, which means it retrieves data without modifying state.
Register the Infra Ops MCP server in PolicyLayer and add a rule for remote_host_inventory: 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 Infra Ops. Nothing to install.
remote_host_inventory 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 remote_host_inventory 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 remote_host_inventory. 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.
remote_host_inventory is provided by the Infra Ops MCP server (skyvanguard/infra-ops-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 →