AI agents call check-port to retrieve information from Ssh without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs network reconnaissance by probing port status and testing connectivity. It only reads/queries network state without modifying data or executing commands. However, port scanning can be used for reconnaissance in attack chains, so severity is low-medium, but the action itself is purely a read/query operation with no side effects.
From the tool's definition Check if a port is open/listening on the remote server or test connectivity to external hosts
Attacks that exploit this kind of access
Check if a port is open/listening on the remote server or test connectivity to external hosts. It is categorised as a Read tool in the Ssh MCP Server, which means it retrieves data without modifying state.
Register the Ssh MCP server in PolicyLayer and add a rule for check-port: 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 Ssh. Nothing to install.
check-port 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 check-port 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 check-port. 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.
check-port is provided by the Ssh MCP server (zachflint/ssh-mcp-server). 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 →