fetch_refund_list
AI agents call fetch_refund_list to retrieve information from Paytm MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'fetch_refund_list' follows the Read pattern (fetch/list operations retrieve data without side effects). However, severity is elevated to 'high' because refund transaction history is sensitive financial data; unauthorized access could expose payment patterns and customer financial information.
From the tool's definition Tool name 'fetch_refund_list' indicates data retrieval. No description provided, but sibling tools on this Paytm payment server include 'check_refund_status' and 'initiate_refund', establishing this as a refund-management context.
Attacks that exploit this kind of access
fetch_refund_list. It is categorised as a Read tool in the Paytm MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Paytm MCP Server MCP server in PolicyLayer and add a rule for fetch_refund_list: 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 Paytm MCP Server. Nothing to install.
fetch_refund_list 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 fetch_refund_list 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 fetch_refund_list. 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.
fetch_refund_list is provided by the Paytm MCP Server MCP server (shivam3-garg/payment-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 →