Fetches Radar risk data, early fraud warnings, disputes, and refunds for a payment.
AI agents call stripe_fraud_insight to retrieve information from Stripe Fraud MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only operations on payment fraud data including risk assessments, early fraud warnings, disputes, and refund history. While the core action is retrieval (Read category), the data accessed is sensitive financial information that could be misused if exposed to an unauthorized agent. The medium severity reflects the sensitive nature of fraud analysis data rather than any destructive capability.
From the tool's definition Tool fetches Radar risk data, early fraud warnings, disputes, and refunds for a payment. The verb 'Fetches' indicates data retrieval without modification. However, the sensitivity of fraud and payment data elevates severity from low to medium.
Attacks that exploit this kind of access
Fetches Radar risk data, early fraud warnings, disputes, and refunds for a payment. It is categorised as a Read tool in the Stripe Fraud MCP MCP Server, which means it retrieves data without modifying state.
Register the Stripe Fraud MCP server in PolicyLayer and add a rule for stripe_fraud_insight: 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 Stripe Fraud MCP. Nothing to install.
stripe_fraud_insight 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 stripe_fraud_insight 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 stripe_fraud_insight. 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.
stripe_fraud_insight is provided by the Stripe Fraud MCP server (keithah/stripe-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →