Fetch fulfillments that can be returned for an order
AI agents call get_returnable_fulfillments 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 information about fulfillments eligible for return. It queries existing data without creating, modifying, deleting, or executing any operations. The action is purely informational and carries minimal risk if misused by an AI agent.
From the tool's definition Tool name 'get_returnable_fulfillments' and description 'Fetch fulfillments that can be returned for an order' indicate data retrieval only. The verb 'fetch' is a read operation with no side effects.
Attacks that exploit this kind of access
Fetch fulfillments that can be returned for an 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_returnable_fulfillments: 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_returnable_fulfillments 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_returnable_fulfillments 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_returnable_fulfillments. 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_returnable_fulfillments 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 →