Publish a locale to make it available on the storefront
AI agents use publish_locale 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.
This tool creates or modifies configuration data by publishing a locale, making it available to customers. This is a write operation that changes the store's state. It is not destructive because publishing can be reversed by unpublishing.
From the tool's definition Tool name 'publish_locale' combined with description 'Publish a locale to make it available on the storefront' indicates a state-change operation that modifies storefront configuration. The action is reversible (a locale can be unpublished).
Attacks that exploit this kind of access
Publish a locale to make it available on the storefront. 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 publish_locale: 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.
publish_locale 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 publish_locale 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 publish_locale. 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.
publish_locale 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 →