Score a draft script for viral potential with a mitigation-aware adversarial second-pass. Returns optimistic_score (upstream self-grade), virality_score (adversarial headline), calibration_gap (disagreement between them), vectors_summary (counts of present vs mitigated attack vectors), recommenda...
Risk signalsAccepts freeform code/query input (script) · Bulk/mass operation — affects multiple targets
Part of the Hooklayer server.
Free to start. No card required.
AI agents call predict_virality to retrieve information from Hooklayer 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 predict_virality 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": {
"predict_virality": {}
}
}See the full Hooklayer policy for all 7 tools.
These attack patterns abuse exactly the kind of access predict_virality 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.
Score a draft script for viral potential with a mitigation-aware adversarial second-pass. Returns optimistic_score (upstream self-grade), virality_score (adversarial headline), calibration_gap (disagreement between them), vectors_summary (counts of present vs mitigated attack vectors), recommendation ({verdict: SHIP|REWORK|NO-GO, reason}), score_range, viral DNA breakdown, signals[] with evidence, would_fail_because, calibration_check, and attack_vectors[] each tagged status: present|mitigated. USE WHEN the user has a finished draft and wants pre-publish verification, or chained after viral_remix to validate the generated script. Pass either a script string or a video URL. Costs 2 credits. TOOL HEALTH: response includes a quality field (level: full | partial | degraded, plus reason). If level is partial or degraded, flag it in chat before reporting. Never silently route around degraded data. REPORTING (v1.1.1 reframe — calibration gap is the value proposition, not a deficiency): lead with the recommendation.verdict and reason in plain language. Then frame the calibration_gap explicitly: "Every other AI scoring tool ships the OPTIMISTIC value of X without checking. The adversarial pass disagrees by GAP points and lands at VIRALITY_SCORE." Then surface vectors_summary as "X total, Y mitigated by the script, Z still present" and enumerate each PRESENT vector with severity + mitigation hint. Surface would_fail_because and signals[] last. NEVER report optimistic_score alone (recreates the self-grading loop). NEVER apologize for the adversarial number being lower — the gap IS the value. A 24-point gap means the check is doing its job; a 0-point gap means the check is rubber-stamping and worthless.. It is categorised as a Read tool in the Hooklayer MCP Server, which means it retrieves data without modifying state.
Register the Hooklayer MCP server in PolicyLayer and add a rule for predict_virality: 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.
predict_virality 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 predict_virality 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 predict_virality. 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.
predict_virality 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.