Publish a collection to sales channels
AI agents use publish_collection 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.
Publishing a collection changes its visibility and availability on sales channels, which is a data modification action. It is reversible (can be unpublished), so it does not meet the threshold for Destructive. It affects business operations (product discoverability) but does not move money (Financial) or execute arbitrary code (Execute).
From the tool's definition 'Publish a collection to sales channels' — the tool modifies the publication state of a collection, making it visible on specified sales channels. This is a reversible state change (collections can be unpublished).
Attacks that exploit this kind of access
Publish a collection to sales channels. 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_collection: 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_collection 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_collection 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_collection. 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_collection 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 →