finalize_test

THE RISK

Critical Risk

Why finalize_test needs a policy

The tool irreversibly removes code elements (the connect() call) and optionally cleans up markers from the test. Removing code constructs is not easily reversible without version control, making this a Destructive operation. The blast radius is medium since it affects test code rather than production data or systems.

From the tool's definition 'removing connect() call' and 'cleaning up markers' — these are irreversible modifications to test code/state

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

POLICY

How to control finalize_test

PolicyLayer is an MCP gateway — it sits between your AI agents and Testing, and nothing reaches the server without passing your rules. This is the rule we recommend for finalize_test:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "finalize_test"
  ]
}

finalize_test disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

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

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Testing tools

Execute execute_test_step Execute code directly in the connected test client and get back the updated DOM state and Read get_current_test_state Get the current state of a connected test, including DOM, snapshot, console logs, and avai Read get_generated_code Get all generated code blocks from a test file Read list_active_tests List all currently connected test processes

All 5 Testing tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in Testing → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about finalize_test

What does the finalize_test tool do? +

Finalize the test by removing connect() call and optionally cleaning up markers. It is categorised as a Destructive tool in the Testing MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on finalize_test? +

Register the Testing MCP server in PolicyLayer and add a rule for finalize_test: 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 Testing. Nothing to install.

What risk level is finalize_test? +

finalize_test is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit finalize_test? +

Yes. Add a rate_limit block to the finalize_test 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 finalize_test completely? +

Set action: deny in the PolicyLayer policy for finalize_test. 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 finalize_test? +

finalize_test is provided by the Testing MCP server (mcpland/testing-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Testing tool call.

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

CHECK YOUR STACK →