Create a new theme
AI agents use create_theme to create or update resources in Shopify Graphql — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Shopify Graphql environment.
Creating a theme modifies the store's configuration by adding a new asset, but the operation is reversible and does not delete or overwrite existing data (thus not Destructive), does not execute arbitrary code (thus not Execute), and does not involve financial transactions (thus not Financial).
From the tool's definition Tool name 'create_theme' and description 'Create a new theme' indicate the tool creates new data (a theme) in a Shopify store. This is a reversible write operation—themes can be modified or deleted afterward.
Attacks that exploit this kind of access
Create a new theme. It is categorised as a Write tool in the Shopify Graphql MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Shopify Graphql MCP server in PolicyLayer and add a rule for create_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.
create_theme is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_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 create_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.
create_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 →