Return derived finance and payment risk alerts for the selected time window.
AI agents call get_risk_alerts to retrieve information from Stripe Reporting without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries risk alert data from Stripe with no side effects or mutations. It falls squarely in the Read category. Severity is medium rather than low because the data returned (risk alerts) is financially and operationally sensitive; an AI agent with incorrect prompt injection could extract alerts to exfiltrate or misuse financial risk intelligence.
From the tool's definition Tool name 'get_risk_alerts' and description 'Return derived finance and payment risk alerts' indicate data retrieval only.
Attacks that exploit this kind of access
Return derived finance and payment risk alerts for the selected time window. It is categorised as a Read tool in the Stripe Reporting MCP Server, which means it retrieves data without modifying state.
Register the Stripe Reporting MCP server in PolicyLayer and add a rule for get_risk_alerts: 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 Reporting. Nothing to install.
get_risk_alerts 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 get_risk_alerts 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 get_risk_alerts. 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.
get_risk_alerts is provided by the Stripe Reporting MCP server (ohrytskov/stripe-reporting-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 →