screen_fraud
Fraud, velocity and AML/PEP watchlist screening (mock). Returns CLEAR / REVIEW / BLOCK with signals and a score. A REVIEW verdict should pause for human handoff.
This record as markdown: /tools/nitrostack/screen-fraud.md
What screen_fraud does on Nitrostack
AI agents call screen_fraud to permanently remove resources in Nitrostack, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why screen_fraud is rated Critical
An AI agent that decides to call screen_fraud doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Nitrostack is gone. There is no undo for destructive operations.
Attacks that exploit this kind of access
The rule that runs screen_fraud safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nitrostack, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For screen_fraud, this is the rule to start with:
screen_fraud is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Nitrostack, apply this rule, and every screen_fraud call is checked against it from then on.
Questions about screen_fraud
Fraud, velocity and AML/PEP watchlist screening (mock). Returns CLEAR / REVIEW / BLOCK with signals and a score. A REVIEW verdict should pause for human handoff. It is categorised as a Destructive tool in the Nitrostack MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Nitrostack MCP server in PolicyLayer and add a rule for screen_fraud: 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 Nitrostack. Nothing to install.
screen_fraud is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the screen_fraud 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 screen_fraud. 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.
screen_fraud is provided by the Nitrostack MCP server (nitrocloudofficial/nitrostack). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nitrostack, and thousands of servers like it.
Across the catalogue