AI agents call get_agent_ports to retrieve information from Waymark without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries information about TCP ports opened by agent processes. It performs no modifications, deletions, code execution, or financial operations. The action is purely informational and read-only, making it a Read category tool. Severity is low because port information disclosure has minimal immediate security impact compared to command execution or data destruction.
From the tool's definition Tool name is 'get_agent_ports' with description 'List TCP ports opened by AI agent child processes' — the verb 'List' indicates retrieval of information without modification or side effects.
Attacks that exploit this kind of access
List TCP ports opened by AI agent child processes. It is categorised as a Read tool in the Waymark MCP Server, which means it retrieves data without modifying state.
Register the Waymark MCP server in PolicyLayer and add a rule for get_agent_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 Waymark. Nothing to install.
get_agent_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_agent_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_agent_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_agent_ports is provided by the Waymark MCP server (waymarks/waymark). 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 →