Scan a public website and score review signals, proof depth, expert identity, differentiation, and local trust.
AI agents invoke run_trust_stack_audit to trigger actions in Quiet Protocol Growth Offense. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
city | string | — | Primary city or market. |
niche | string | — | Business niche or vertical. |
websiteUrl | string | — | Homepage URL to scan. |
Parameters from the server's own tool schema.
This tool triggers an external operation (website scanning/analysis) that executes against a provided target. While non-destructive and read-focused in its outputs (scoring and analysis), the scanning action itself and its potential to trigger rate limiting, cache impacts, or trigger security alerts on the scanned website classify it as Execute rather than Read.
From the tool's definition Tool performs a 'scan' of a public website and generates scores based on analysis of review signals, proof depth, expert identity, differentiation, and local trust.
Documented attack patterns abuse exactly the kind of access run_trust_stack_audit gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Quiet Protocol Growth Offense, and nothing reaches the server without passing your rules. This is the rule we recommend for run_trust_stack_audit:
{
"version": "1",
"default": "deny",
"tools": {
"run_trust_stack_audit": {
"limits": [
{
"counter": "run_trust_stack_audit_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_trust_stack_audit stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Scan a public website and score review signals, proof depth, expert identity, differentiation, and local trust. It is categorised as a Execute tool in the Quiet Protocol Growth Offense MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
run_trust_stack_audit accepts 3 parameters: city, niche, websiteUrl. The full parameter table on this page comes from the server's own tool schema.
Register the Quiet Protocol Growth Offense MCP server in PolicyLayer and add a rule for run_trust_stack_audit: 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 Quiet Protocol Growth Offense. Nothing to install.
run_trust_stack_audit is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_trust_stack_audit 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 run_trust_stack_audit. 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.
run_trust_stack_audit is provided by the Quiet Protocol Growth Offense MCP server (joeroy2027/tqp-site). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Quiet Protocol Growth Offense, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
19 Quiet Protocol Growth Offense tools catalogued and risk-classified — across an index of 43,000+ MCP servers.