Fetch Razorpay refunds for a date range. Retrieves refund details including amount, payment_id, and status. Use this to check refund volumes, verify refund statuses, or detect refund anomalies. Args: from_date: Start date (YYYY-MM-DD). Defaults to yesterday. to_date: End date (YYYY-MM-DD). Defaul...
AI agents call get_refunds to retrieve information from Razorpay Recon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure read operation that queries refund data from Razorpay. However, severity is elevated to 'medium' rather than 'low' because refund data contains sensitive financial transaction information (amounts, payment IDs, status) that could be misused if exfiltrated by a compromised agent.
From the tool's definition Tool description explicitly states 'Fetch Razorpay refunds' and 'Retrieves refund details including amount, payment_id, and status.' The parameters (from_date, to_date) enable querying historical data.
Attacks that exploit this kind of access
Fetch Razorpay refunds for a date range. Retrieves refund details including amount, payment_id, and status. Use this to check refund volumes, verify refund statuses, or detect refund anomalies. Args: from_date: Start date (YYYY-MM-DD). Defaults to yesterday. to_date: End date (YYYY-MM-DD). Defaults to today. Returns: List of refunds with id, payment_id, amount (in paise), and status. It is categorised as a Read tool in the Razorpay Recon MCP Server, which means it retrieves data without modifying state.
Register the Razorpay Recon MCP server in PolicyLayer and add a rule for get_refunds: 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 Razorpay Recon. Nothing to install.
get_refunds 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_refunds 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_refunds. 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_refunds is provided by the Razorpay Recon MCP server (qalalabs/razorpay-recon-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 →