SENSITIVE: Open Stripe Dashboard to process refunds. For security, refunds are processed through the Stripe Dashboard interface. This opens your browser to the refund management page.
Part of the Ra Pay server.
Free to start. No card required.
AI agents use ra_refund to initiate financial transactions through Ra Pay. Financial operations involve real money and are irreversible once processed. PolicyLayer blocks financial tools by default, requiring explicit human approval with transaction-level limits to prevent unauthorised spending.
ra_refund moves real money. Without a policy, an autonomous agent could initiate transactions that drain accounts or exceed budgets. PolicyLayer blocks financial tools by default, requiring human-in-the-loop approval with configurable spending limits per transaction and per time window.
Financial tools involve real money. Block by default and require explicit human approval before enabling.
{
"version": "1",
"default": "deny",
"tools": {
"ra_refund": {
"deny_if": [
{
"conditions": [],
"on_deny": "Requires human approval."
}
]
}
}
} See the full Ra Pay policy for all 8 tools.
These attack patterns abuse exactly the kind of access ra_refund gives an agent. Each links to the full case and the policy that stops it:
Other financial tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
SENSITIVE: Open Stripe Dashboard to process refunds. For security, refunds are processed through the Stripe Dashboard interface. This opens your browser to the refund management page.. It is categorised as a Financial tool in the Ra Pay MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Ra Pay MCP server in PolicyLayer and add a rule for ra_refund: 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 Ra Pay. Nothing to install.
ra_refund is a Financial 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 ra_refund 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 ra_refund. 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.
ra_refund is provided by the Ra Pay MCP server (@rapay/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Ra Pay tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.