Fetch returns for a specific order
AI agents call get_returns_by_order to retrieve information from Shopify Graphql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves return data associated with a Shopify order. The verb 'fetch' clearly indicates a read-only operation that queries existing data without side effects. There is no creation, modification, deletion, code execution, or financial transaction involved. The data retrieved is informational and does not alter any state in the system.
From the tool's definition Tool name 'get_returns_by_order' and description 'Fetch returns for a specific order' indicate a query/retrieval operation with no modification or execution of external operations.
Attacks that exploit this kind of access
Fetch returns for a specific order. It is categorised as a Read tool in the Shopify Graphql MCP Server, which means it retrieves data without modifying state.
Register the Shopify Graphql MCP server in PolicyLayer and add a rule for get_returns_by_order: 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 Shopify Graphql. Nothing to install.
get_returns_by_order 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_returns_by_order 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_returns_by_order. 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_returns_by_order is provided by the Shopify Graphql MCP server (uvu-store/shopify-graphql-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 →