Fetch script tags from the Shopify store
AI agents call get_script_tags 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' and the absence of any create, update, delete, or execute language confirms this is a read-only query operation. Script tags are metadata/configuration objects being retrieved, not executed or modified. The blast radius of misclassification is minimal—an AI reading script tag information cannot cause direct harm without additional tools.
From the tool's definition Tool name 'get_script_tags' and description 'Fetch script tags from the Shopify store' indicate data retrieval with no mutation or side effects.
Attacks that exploit this kind of access
Fetch script tags 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_script_tags: 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_script_tags 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_script_tags 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_script_tags. 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_script_tags 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 →