Deep intelligence on a TikTok or YouTube creator by handle. Returns viral DNA scores (viral_dna_score, replicability_score, originality_score, consistency_score, audience_fatigue), format fingerprint, top 5 recent videos with metadata (and transcripts on TikTok), content gaps, AND a recommended_c...
Risk signalsBulk/mass operation — affects multiple targets
Part of the Hooklayer server.
Free to start. No card required.
AI agents call analyze_account 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 analyze_account 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": {
"analyze_account": {}
}
}See the full Hooklayer policy for all 7 tools.
These attack patterns abuse exactly the kind of access analyze_account 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.
Deep intelligence on a TikTok or YouTube creator by handle. Returns viral DNA scores (viral_dna_score, replicability_score, originality_score, consistency_score, audience_fatigue), format fingerprint, top 5 recent videos with metadata (and transcripts on TikTok), content gaps, AND a recommended_chain field with pre-filled next tool calls. USE WHEN the user references a creator by @handle, asks "analyze X", wants competitor research, or needs creator context before generating content. The recommended_chain suggests which tools to call next (match_voice, trend_pulse, viral_remix) with parameters pre-filled — review and execute them as appropriate. Supports platform: "tiktok" (default, full transcript extraction) and "youtube" (channel Shorts analysis; transcript extraction lands in v1.1, current YouTube responses surface a partial-data flag noting this). Costs 5 credits. 1-hour cache per (handle, platform). TOOL HEALTH: Every response includes a quality field with a level (full | partial | degraded) and a reason. If quality.level is partial or degraded, you MUST flag this to the user explicitly in chat (e.g. "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 viral_dna.viral_dna_signals, viral_dna.replicability_signals, viral_dna.originality_signals (each as bullet lists with the cited evidence string verbatim) AND viral_dna.would_fail_because verbatim AND provenance.video_post_dates so the user can see freshness. Never hide the evidence array behind a paraphrase — these are the auditability layer.. 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 analyze_account: 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.
analyze_account 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 analyze_account 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 analyze_account. 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.
analyze_account 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.