AI agents call list_configured_hosts to retrieve information from Mcp Ssh without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward read operation that queries and returns SSH host configuration data. While the host information could theoretically be sensitive (IP addresses, hostnames), the tool itself performs no modifications or operations—it merely retrieves and displays existing configuration. This is the lowest-risk category among the available options.
From the tool's definition Tool name 'list_configured_hosts' and description 'List all SSH hosts configured in SSH_HOSTS_JSON' indicate a retrieval/query operation with no side effects.
Attacks that exploit this kind of access
List all SSH hosts configured in SSH_HOSTS_JSON. It is categorised as a Read tool in the Mcp Ssh MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ssh MCP server in PolicyLayer and add a rule for list_configured_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 Ssh. Nothing to install.
list_configured_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_configured_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_configured_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_configured_hosts is provided by the Mcp Ssh MCP server (zhouxiangjing/mcp-ssh). 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 →