Delete a theme
AI agents call delete_theme to permanently remove resources in Shopify Graphql — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a theme from a Shopify store, which cannot be undone. Deletion is irreversible and has a significant blast radius—a compromised agent could remove active themes, disrupting store operations. This clearly falls under the Destructive category, which supersedes all others in severity hierarchy.
From the tool's definition Tool name: 'delete_theme'; Tool description: 'Delete a theme'. The verb 'delete' indicates irreversible removal of data (a theme/storefront template).
Attacks that exploit this kind of access
Delete a theme. It is categorised as a Destructive tool in the Shopify Graphql MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Shopify Graphql MCP server in PolicyLayer and add a rule for delete_theme: 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.
delete_theme is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_theme 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 delete_theme. 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.
delete_theme 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 →