get_refund_list
AI agents call get_refund_list to retrieve information from Pypi:mcp Cn Commerce without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix combined with 'read-only access' server description and sibling tool patterns (get_after_sale_list, get_bill_list, etc.) indicate this is a data retrieval operation with no side effects. However, refund data is sensitive business/financial information, warranting medium severity due to potential exposure of transaction details, customer information, and financial records if misused by an agent.
From the tool's definition Tool name is 'get_refund_list' and server description states it provides 'read-only access' to e-commerce platform business data. Sibling tools are all 'get_*' operations indicating query/retrieval functions.
Attacks that exploit this kind of access
get_refund_list. It is categorised as a Read tool in the Pypi:mcp Cn Commerce MCP Server, which means it retrieves data without modifying state.
Register the Pypi:mcp Cn Commerce MCP server in PolicyLayer and add a rule for get_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 Pypi:mcp Cn Commerce. Nothing to install.
get_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 get_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 get_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.
get_refund_list is provided by the Pypi:mcp Cn Commerce MCP server (tonywang-hub/mcp-cn-commerce). 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 →