Retrieve refund information by ID
AI agents call retrieve_refund to retrieve information from Omise MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries existing refund data by identifier. It performs a read-only operation returning refund details without creating, modifying, deleting, or executing any transactions. While it operates in a payment processing context, the retrieve operation itself carries minimal risk as it only accesses information that should already be accessible to authorized users.
From the tool's definition Tool name 'retrieve_refund' and description 'Retrieve refund information by ID' indicate a data retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Retrieve refund information by ID. It is categorised as a Read tool in the Omise MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Omise MCP Server MCP server in PolicyLayer and add a rule for retrieve_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 Omise MCP Server. Nothing to install.
retrieve_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 retrieve_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 retrieve_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.
retrieve_refund is provided by the Omise MCP Server MCP server (jun-omise/omise-mcp-alpha). 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 →