AI agents call check_slug_available to retrieve information from IOX Cloud without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple lookup to verify if a subdomain slug is available. It has no side effects, does not commit resources, does not execute code, and does not modify state. It is a read-only query similar to 'get' or 'check' operations. The blast radius of misuse is minimal—an attacker could enumerate available slugs but cannot disrupt service or cause harm.
From the tool's definition Tool name 'check_slug_available' and description 'Check whether a subdomain slug is available' indicate a query operation that retrieves availability status without modifying, creating, deleting, or executing anything.
Attacks that exploit this kind of access
Check whether a subdomain slug is available for deployment at {slug}.iox.cloud. It is categorised as a Read tool in the IOX Cloud MCP Server, which means it retrieves data without modifying state.
Register the IOX Cloud MCP server in PolicyLayer and add a rule for check_slug_available: 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 IOX Cloud. Nothing to install.
check_slug_available 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_slug_available 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_slug_available. 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_slug_available is provided by the IOX Cloud MCP server (meruada/iox-cloud-mcp). 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 →