AI agents call get_open_ports 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 tool queries network information (netstat/ss output) and returns data about listening ports and processes. It has no side effects, does not execute commands beyond introspection, and does not modify system state. While it reveals security-relevant information that could inform reconnaissance, the tool itself performs only data retrieval.
From the tool's definition Tool description states 'List all open listening ports and their associated processes' — a pure read operation that retrieves system state without modification.
Attacks that exploit this kind of access
List all open listening ports and their associated processes. 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 get_open_ports: 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.
get_open_ports 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 get_open_ports 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 get_open_ports. 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.
get_open_ports 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 →