Unlink an official mirror queue entry from its linked MCP server. This is a synchronous operation. This action: 1. Removes the mcp_server_id from all mirrors in this queue entry 2. Resets the queue entry status to pending (pending_new or pending_update based on history) 3. The previously linked s...
AI agents use unlink_official_mirror_queue_item 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.
This tool modifies queue entry data by removing a server linkage and resetting status. It is reversible (the entry returns to pending and can be re-linked), so it falls under Write rather than Destructive. The blast radius is medium since it affects queue processing workflows but does not permanently destroy data.
From the tool's definition Removes the mcp_server_id from all mirrors in this queue entry; Resets the queue entry status to pending; The previously linked server is not modified
Documented attack patterns abuse exactly the kind of access unlink_official_mirror_queue_item 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 unlink_official_mirror_queue_item:
{
"version": "1",
"default": "deny",
"tools": {
"unlink_official_mirror_queue_item": {
"limits": [
{
"counter": "unlink_official_mirror_queue_item_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}unlink_official_mirror_queue_item 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.
Unlink an official mirror queue entry from its linked MCP server. This is a synchronous operation. This action: 1. Removes the mcp_server_id from all mirrors in this queue entry 2. Resets the queue entry status to pending (pending_new or pending_update based on history) 3. The previously linked server is not modified Use cases: - Correct a mistaken server linkage - Re-process a queue entry with a different server - Reset an entry for re-evaluation - Unlink before linking to a different server Note: After unlinking, the queue entry will return to pending status and can be: - Approved again with a different server (approve_official_mirror_queue_item) - Added to the regular queue as a new draft (add_official_mirror_to_regular_queue) - Rejected (reject_official_mirror_queue_item). 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 unlink_official_mirror_queue_item: 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.
unlink_official_mirror_queue_item 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 unlink_official_mirror_queue_item 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 unlink_official_mirror_queue_item. 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.
unlink_official_mirror_queue_item 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.