Score a TikTok/Reels/Shorts hook against proven viral patterns. Returns a 0-100 score, percentile rank, matched viral pattern, three rewritten versions at higher quality, a one-sentence verdict naming the closest calibration anchor (10/30/50/70/85/95), a 6-element signals[] array with evidence pe...
Risk signalsBulk/mass operation — affects multiple targets
Part of the Hooklayer server.
Free to start. No card required.
AI agents may call score_hook to permanently remove or destroy resources in Hooklayer. 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 score_hook in a loop, permanently destroying resources in Hooklayer. 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": [
"score_hook"
]
}See the full Hooklayer policy for all 7 tools.
These attack patterns abuse exactly the kind of access score_hook 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.
Score a TikTok/Reels/Shorts hook against proven viral patterns. Returns a 0-100 score, percentile rank, matched viral pattern, three rewritten versions at higher quality, a one-sentence verdict naming the closest calibration anchor (10/30/50/70/85/95), a 6-element signals[] array with evidence per sub-score, and a would_fail_because counterfactual. USE WHEN the user has a draft hook to validate, wants to A/B between alternatives, or needs to catch AI-generated slop before publishing. Pairs after viral_remix to verify the generated hook. Costs 1 credit. TOOL HEALTH: Every response includes a quality: { level: "full" | "partial" | "degraded", reason?: string } field. If quality.level is "partial" or "degraded", you MUST flag this to the user explicitly in chat ("Heads up — this call returned partial data: <reason>") before reporting any results. Never silently route around a degraded response. REPORTING: When you summarize this in chat, you MUST surface (a) the score paired with the closest anchor from the why field, (b) the signals[] array as a bullet list with each evidence string verbatim — never paraphrase or drop signals, and (c) the would_fail_because field verbatim. If you score multiple hooks in sequence, also explicitly compare their signals[], not just the numeric scores — that's how the user judges which one wins.. It is categorised as a Destructive tool in the Hooklayer MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Hooklayer MCP server in PolicyLayer and add a rule for score_hook: 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 Hooklayer. Nothing to install.
score_hook 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 score_hook 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 score_hook. 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.
score_hook is provided by the Hooklayer MCP server (https://hooklayer.dev/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 Hooklayer 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.