Fetch resource feedbacks from the Shopify store
AI agents call get_resource_feedbacks 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.
The verb 'fetch' combined with the absence of any language suggesting data modification, deletion, or external execution clearly indicates this is a read-only operation. It retrieves feedback data without altering store state. Low severity because feedback data is typically non-sensitive customer review information and retrieval poses minimal risk to store integrity.
From the tool's definition Tool name 'get_resource_feedbacks' and description 'Fetch resource feedbacks from the Shopify store' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Fetch resource feedbacks from the Shopify store. 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_resource_feedbacks: 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_resource_feedbacks 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_resource_feedbacks 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_resource_feedbacks. 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_resource_feedbacks 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 →