AI agents call port_check to retrieve information from Keel without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the state of a network port without modifying, executing commands on, or damaging any system. It is a network diagnostic read operation similar to ping or DNS lookup. While port scanning information could theoretically inform an attacker, the tool itself performs only reconnaissance (Read category) rather than exploitation.
From the tool's definition Tool name 'port_check' and description 'Check whether a single TCP port is open on a host' indicate a read-only query operation. The verb 'check' and the passive phrasing 'whether a port is open' confirm this is diagnostic/informational with no side effects.
Attacks that exploit this kind of access
Check whether a single TCP port is open on a host. It is categorised as a Read tool in the Keel MCP Server, which means it retrieves data without modifying state.
Register the Keel MCP server in PolicyLayer and add a rule for port_check: 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 Keel. Nothing to install.
port_check 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 port_check 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 port_check. 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.
port_check is provided by the Keel MCP server (seayniclabs/keel). 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 →