Enable or disable a deliberate, auditable ONE-OFF bypass of the SYSTEMIC_DROP guardrail in the popularity-estimates pipeline. Background: UpdatePopularityEstimatesFromBigqueryJob holds large downward popularity corrections when more than ~10% of servers would drop at once (a possible systemic ups...
AI agents use set_popularity_drop_bypass to create or update resources in Playwright Stealth — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Playwright Stealth environment.
The tool modifies pipeline behavior and data handling for popularity estimates rather than performing irreversible deletion. While it affects a guardrail system, it is toggling a bypass flag on/off (reversible state change) rather than destructively removing data. The impact is a change in how data is processed and corrected in the next job run, which constitutes a Write operation.
From the tool's definition Tool enables or disables a bypass of a guardrail in the popularity-estimates pipeline. Description indicates it affects data correction behavior: 'keeping each flagged server at its stale value' versus allowing popularity updates to proceed.
Documented attack patterns abuse exactly the kind of access set_popularity_drop_bypass gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright Stealth, and nothing reaches the server without passing your rules. This is the rule we recommend for set_popularity_drop_bypass:
{
"version": "1",
"default": "deny",
"tools": {
"set_popularity_drop_bypass": {
"limits": [
{
"counter": "set_popularity_drop_bypass_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}set_popularity_drop_bypass stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Enable or disable a deliberate, auditable ONE-OFF bypass of the SYSTEMIC_DROP guardrail in the popularity-estimates pipeline. Background: UpdatePopularityEstimatesFromBigqueryJob holds large downward popularity corrections when more than ~10% of servers would drop at once (a possible systemic upstream event), keeping each flagged server at its stale value for ~3 days. During a known-legitimate remediation wave (e.g. correcting servers mis-linked to famous registry packages), that guardrail keeps genuinely-corrected servers visible at inflated values. Enabling this bypass tells the NEXT job run to skip the SYSTEMIC_DROP hold for that single run only: it applies the corrected (dropped) BigQuery values, clears popularity_drop_held_since for the affected servers, then CONSUMES the flag (auto-resets enabled→false). The independent impossible-RISE guardrail is unaffected. Returns the resulting bypass status (enabled / enabled_at / enabled_by). Use cases: - Enable the bypass before the next scheduled run to flush a known-legitimate correction wave caught in a systemic hold - Disable the bypass if it was enabled in error and the next run has not yet consumed it. It is categorised as a Write tool in the Playwright Stealth MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Playwright Stealth MCP server in PolicyLayer and add a rule for set_popularity_drop_bypass: 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 Playwright Stealth. Nothing to install.
set_popularity_drop_bypass 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 set_popularity_drop_bypass 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 set_popularity_drop_bypass. 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.
set_popularity_drop_bypass is provided by the Playwright Stealth MCP server (pulsemcp/mcp-servers). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Playwright Stealth, 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.
68 Playwright Stealth tools catalogued and risk-classified — across an index of 43,000+ MCP servers.