HEAD-equivalent: returns HTTP status_code + ok bool. Uses full browser (cookies, JS).
AI agents call check_website_status to retrieve information from Nexus Core without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves HTTP status information from a website. Although it uses a full browser with cookies and JavaScript execution, the purpose is read-only: checking whether a site is online and retrieving its response code. There are no data mutations, deletions, or irreversible actions. The JavaScript execution is necessary context for the request but does not modify state on the target server or elsewhere.
From the tool's definition The tool 'returns HTTP status_code + ok bool' and performs a HEAD-equivalent operation, which queries state without modification.
Attacks that exploit this kind of access
HEAD-equivalent: returns HTTP status_code + ok bool. Uses full browser (cookies, JS). It is categorised as a Read tool in the Nexus Core MCP Server, which means it retrieves data without modifying state.
Register the Nexus Core MCP server in PolicyLayer and add a rule for check_website_status: 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 Nexus Core. Nothing to install.
check_website_status 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_website_status 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_website_status. 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_website_status is provided by the Nexus Core MCP server (noumenon-ai/nexus-core). 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 →