invoice_fraud_check
Rule-based fraud risk for an invoice (duplicate / vendor-anomaly / round-amount / rush-terms) → score 0-100 + LOW/MEDIUM/HIGH/CRITICAL + reasons. Deterministic, no keys.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/invoice-fraud-check.md
What invoice_fraud_check does on Gateway
AI agents call invoice_fraud_check to retrieve information from Gateway without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
invoice | object | Yes | the invoice to score |
existing_invoices | array | — | prior invoices for duplicate/vendor-anomaly checks |
Parameters from the server's own tool schema.
Why invoice_fraud_check is rated Low
This tool reads and analyzes invoice data to produce a fraud risk assessment score. It queries/evaluates attributes and returns analysis results without creating, modifying, deleting, or executing any external operations. The deterministic, stateless nature and lack of side effects confirm this is a Read operation—similar to a fraud detection classifier that inspects but does not alter data or trigger transactions.
From the tool's definition Tool performs rule-based analysis and scoring of invoice attributes (duplicate, vendor-anomaly, round-amount, rush-terms) and returns a risk score with classification and reasons. No modification, deletion, or execution of external systems occurs.
Attacks that exploit this kind of access
The rule that runs invoice_fraud_check safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For invoice_fraud_check, this is the rule to start with:
invoice_fraud_check is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Gateway, apply this rule, and every invoice_fraud_check call is checked against it from then on.
Questions about invoice_fraud_check
Rule-based fraud risk for an invoice (duplicate / vendor-anomaly / round-amount / rush-terms) → score 0-100 + LOW/MEDIUM/HIGH/CRITICAL + reasons. Deterministic, no keys. It is categorised as a Read tool in the Gateway MCP Server, which means it retrieves data without modifying state.
invoice_fraud_check accepts 2 parameters: invoice, existing_invoices. Required: invoice. The full parameter table on this page comes from the server's own tool schema.
Register the Gateway MCP server in PolicyLayer and add a rule for invoice_fraud_check: 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 Gateway. Nothing to install.
invoice_fraud_check is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the invoice_fraud_check 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 invoice_fraud_check. 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.
invoice_fraud_check is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gateway, and thousands of servers like it.
This server
Across the catalogue