Search for unregistered short .ai domains. Find rare 3-letter and 4-letter pattern domains still available for registration. Pattern types: - CVCV: Consonant-Vowel-Consonant-Vowel (e.g., 'bora', 'mito') — most brandable, sounds like real words. - VCVC: Vowel-Consonant-Vowel-Consonant (e.g., 'amon...
Part of the DomainKits server.
Free to start. No card required.
AI agents call unregistered_ai to retrieve information from DomainKits without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though unregistered_ai only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"unregistered_ai": {}
}
}See the full DomainKits policy for all 38 tools.
These attack patterns abuse exactly the kind of access unregistered_ai gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Search for unregistered short .ai domains. Find rare 3-letter and 4-letter pattern domains still available for registration. Pattern types: - CVCV: Consonant-Vowel-Consonant-Vowel (e.g., 'bora', 'mito') — most brandable, sounds like real words. - VCVC: Vowel-Consonant-Vowel-Consonant (e.g., 'amon', 'ivan') — name-like quality. - CCVV: Double consonant + double vowel (e.g., 'bloo', 'staa') — unique/distinctive. - 3letter: Any remaining 3-letter .ai domains — extremely rare and high-value. Best practices: - For brandable names: use type=CVCV or type=VCVC, sort=count_desc to surface names with validated demand across other TLDs. - For undiscovered gems: use tld_count=0-10, sort=count_asc — low cross-TLD registration may indicate overlooked opportunities. - For ultra-premium: use type=3letter — 3-letter .ai domains are the scarcest inventory. - tld_count interpretation: high (50+) = validated demand, the name is desirable across TLDs; low (<10) = less widely registered, may be undiscovered or niche. - Always verify availability with the 'available' tool before recommending registration — availability can change at any time. - .ai is the premium TLD for AI/tech companies; short .ai domains are high-value due to scarcity.. It is categorised as a Read tool in the DomainKits MCP Server, which means it retrieves data without modifying state.
Register the DomainKits MCP server in PolicyLayer and add a rule for unregistered_ai: 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 DomainKits. Nothing to install.
unregistered_ai 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 unregistered_ai 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 unregistered_ai. 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.
unregistered_ai is provided by the DomainKits MCP server (https://api.domainkits.com/v1/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 38 DomainKits tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.