Fetch shop policies (refund, privacy, terms of service, etc.)
AI agents call get_shop_policies 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 existing shop policy documents (refund, privacy, terms of service). Fetching and reading static policy data produces no side effects, no data modifications, and no external operations. It is a straightforward read operation on publicly-facing configuration data. Severity is low because misuse by an AI agent would only expose information that is typically publicly available.
From the tool's definition Tool name is 'get_shop_policies' with description 'Fetch shop policies' — the verb 'Fetch' indicates retrieval without side effects or modifications.
Attacks that exploit this kind of access
Fetch shop policies (refund, privacy, terms of service, etc.). 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_shop_policies: 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_shop_policies 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_shop_policies 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_shop_policies. 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_shop_policies 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 →