save_results_for_mirror

THE RISK

Medium Risk

Why save_results_for_mirror needs a policy

The tool creates or modifies exam result data for an unofficial mirror. This is a Write operation (reversible data modification) rather than Read (no query-only access), Execute (no code execution), or Destructive (results can be updated/corrected).

From the tool's definition Tool name includes 'save_results' and description states 'Save proctor exam results for an unofficial mirror' — indicates modification/creation of exam result records.

Documented attack patterns abuse exactly the kind of access save_results_for_mirror gives an agent:

POLICY

How to control save_results_for_mirror

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 save_results_for_mirror:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "save_results_for_mirror": {
      "limits": [
        {
          "counter": "save_results_for_mirror_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

save_results_for_mirror 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.

Create a free account and register Playwright Stealth — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Playwright Stealth tools

Destructive delete_calendar_event Deletes an event from Google Calendar. Destructive delete_mcp_json Delete an MCP JSON configuration by its ID. This action is irreversible. Use cases: - Rem Destructive delete_redirect Delete a URL redirect by its ID. This action is irreversible. Use cases: - Remove duplica Destructive delete_unofficial_mirror Delete an unofficial mirror by its ID. This action is irreversible. Use cases: - Remove d Destructive deleteEnvVars Delete one or more environment variables from your Rails application on Hatchbox. This too Destructive destroy_machine Delete a Fly.io machine. Permanently removes a Fly machine that was used for Proctor exam Destructive discard_good_job Discard a GoodJob background job. Marks the job as discarded so it will not be retried. U Destructive remove_servers_from_tenant Remove MCP servers from a tenant

All 68 Playwright Stealth tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about save_results_for_mirror

What does the save_results_for_mirror tool do? +

Save proctor exam results for an unofficial mirror. Pass the \. 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.

How do I enforce a policy on save_results_for_mirror? +

Register the Playwright Stealth MCP server in PolicyLayer and add a rule for save_results_for_mirror: 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.

What risk level is save_results_for_mirror? +

save_results_for_mirror is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit save_results_for_mirror? +

Yes. Add a rate_limit block to the save_results_for_mirror 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.

How do I block save_results_for_mirror completely? +

Set action: deny in the PolicyLayer policy for save_results_for_mirror. 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.

What MCP server provides save_results_for_mirror? +

save_results_for_mirror 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.

Enforce policy on every Playwright Stealth tool call.

Start from Playwright Stealth, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →