Trend discovery and domain opportunity workflow. Call when a user wants to explore what keywords are trending in domain registrations and whether those trends represent real investment opportunities. When to use: User asks what's trending, wants to find opportunities based on registration momentu...
Part of the DomainKits server.
Free to start. No card required.
AI agents may call trend_hunter to permanently remove or destroy resources in DomainKits. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call trend_hunter in a loop, permanently destroying resources in DomainKits. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
{
"version": "1",
"default": "deny",
"hide": [
"trend_hunter"
]
}See the full DomainKits policy for all 38 tools.
These attack patterns abuse exactly the kind of access trend_hunter gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
Trend discovery and domain opportunity workflow. Call when a user wants to explore what keywords are trending in domain registrations and whether those trends represent real investment opportunities. When to use: User asks what's trending, wants to find opportunities based on registration momentum, or wants to explore hot/emerging keywords. Not for analyzing a specific domain (use analyze), deep-diving a known keyword (use keyword_intel), or getting a market news briefing (use market_beat). This is a MULTI-TURN workflow. Present findings at each phase and wait for the user to choose direction before proceeding. Do not batch all phases into a single response. Let users choose which keywords to explore — do not decide for them. Methodology — three phases, each gated by user input: 1. Discover: Surface trending keywords using keywords_trends (hot, emerging, or prefix depending on user interest). The results already include pre-computed quality metrics for hot and emerging types: com_ratio, digit_ratio, most_tld, and most_tld_ratio. Present the data with quality assessment: - com_ratio above 0.15 = genuine interest; below 0.05 = likely bulk speculation on cheap TLDs. - most_tld_ratio above 0.7 on a non-.com TLD = trend driven by bulk registration, not organic demand. - digit_ratio above 0.2 = low-quality speculative registrations. Flag any keywords with suspicious quality signals. Ask the user which keyword(s) they want to investigate further. Stop and wait. 2. Assess market catalyst: For the user's chosen keyword, investigate what is driving the trend. - web_search is MANDATORY — do not substitute with your own knowledge. Execute at least two separate searches: one for domain transaction history (e.g., '{keyword} domain sold price 2026') and one for industry news (e.g., '{keyword} news 2026'). Domain transactions are the single strongest catalyst for registration spikes — a high-value sale (e.g., keyword.com selling for six or seven figures) routinely triggers a wave of speculative registrations on the same keyword. Always check for this first. Industry news (product launches, funding rounds, regulatory changes) is the second catalyst layer. If neither search returns relevant results, state that clearly — do not fill the gap with training data. - Synthesize the quality metrics from Phase 1 with the catalyst research into a clear verdict: real trend (strong quality metrics + identifiable catalyst), speculative (weak quality metrics or no catalyst), or uncertain. Present the assessment and recommended search direction. Stop and wait for user confirmation before searching for domains. 3. Find opportunities: Based on the assessment, search for available domains. - deleted and expired for domains available at registration cost or via backorder. - aged with has_sale=true for secondary market listings. - All domains presented to the user MUST be verified via bulk_available before recommending. - Disclose affiliate links. After presenting opportunities, offer relevant next steps: deep analysis on a specific domain (analyze), brand conflict check (brand_match), monitoring setup (set_monitor), or exploring a different keyword.. It is categorised as a Destructive tool in the DomainKits MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the DomainKits MCP server in PolicyLayer and add a rule for trend_hunter: 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.
trend_hunter is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the trend_hunter 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 trend_hunter. 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.
trend_hunter 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.