AI agents call get_refund to retrieve information from Paymongo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about an existing refund without modifying, deleting, or creating any data. It is a straightforward read operation that retrieves refund details by identifier. While it operates in a financial domain, the action itself does not move money or commit financial obligations—it merely accesses existing transaction records.
From the tool's definition Tool name contains 'get_refund' and description states 'Retrieve a refund by its ID.' The verb 'retrieve' and the read-only nature of fetching an existing refund record indicate no side effects or data modification.
Attacks that exploit this kind of access
Retrieve a refund by its ID. It is categorised as a Read tool in the Paymongo MCP Server, which means it retrieves data without modifying state.
Register the Paymongo MCP server in PolicyLayer and add a rule for get_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 Paymongo. Nothing to install.
get_refund 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_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 get_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.
get_refund is provided by the Paymongo MCP server (theyahia/paymongo-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 →