AI agents call ssh_hosts to retrieve information from Mcpx without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays SSH host configuration information from ssh_config and inventory files. It performs no modifications, deletions, code execution, or financial operations. While the information could theoretically inform malicious targeting, the tool itself is purely informational.
From the tool's definition Tool name 'ssh_hosts' and description 'Show the resolved host inventory' indicate a query/retrieval operation with no side effects. The verb 'show' and action of displaying inventory data are characteristic of Read operations.
Attacks that exploit this kind of access
Show the resolved host inventory (ssh_config + inventory file). It is categorised as a Read tool in the Mcpx MCP Server, which means it retrieves data without modifying state.
Register the Mcpx MCP server in PolicyLayer and add a rule for ssh_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 Mcpx. Nothing to install.
ssh_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 ssh_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 ssh_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.
ssh_hosts is provided by the Mcpx MCP server (rmednitzer/relay-shell). 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 →