Extract a creator's voice DNA from 3+ reference samples (URLs or text) and rewrite a draft in their voice. Returns voice profile (energy, humor, vocabulary, signature moves), reusable prompt instructions, the rewritten draft, AND a deterministic voice_metrics block: vocab_diversity_ttr (type-toke...
Risk signalsBulk/mass operation — affects multiple targets
Part of the Hooklayer server.
Free to start. No card required.
AI agents use match_voice to create or modify resources in Hooklayer. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call match_voice repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Hooklayer.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"match_voice": {
"limits": [
{
"counter": "match_voice_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Hooklayer policy for all 7 tools.
These attack patterns abuse exactly the kind of access match_voice gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Extract a creator's voice DNA from 3+ reference samples (URLs or text) and rewrite a draft in their voice. Returns voice profile (energy, humor, vocabulary, signature moves), reusable prompt instructions, the rewritten draft, AND a deterministic voice_metrics block: vocab_diversity_ttr (type-token ratio), filler_rate_per_100_words, avg_sentence_length_words, total_words, and signature_phrases[] (top 5 recurring 2-3-grams with counts). USE WHEN the user wants to write in another creator's style, has reference content to match, or chained from analyze_account.recommended_chain (which pre-fills reference_samples from the analyzed creator's videos). Costs 2 credits. TOOL HEALTH: Every response includes a quality field (level: full | partial | degraded, plus a reason string). 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 the voice_metrics block as numbers — TTR, filler rate, avg sentence length, and the top signature_phrases with their counts. The qualitative voice_profile labels (energy, personality) alone are vibes; the numeric metrics are the reproducible signature. Cite both.. It is categorised as a Write tool in the Hooklayer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Hooklayer MCP server in PolicyLayer and add a rule for match_voice: 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.
match_voice is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the match_voice 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 match_voice. 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.
match_voice 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.