Unpublish a collection from sales channels
AI agents use unpublish_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.
Unpublishing a collection removes its visibility from sales channels but does not delete the collection itself — it is reversible by republishing. This is a modification of the collection's published state, fitting the Write category. Misuse could hide products from customers, causing revenue impact, hence medium severity.
From the tool's definition Unpublish a collection from sales channels
Attacks that exploit this kind of access
Unpublish a collection from 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 unpublish_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.
unpublish_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 unpublish_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 unpublish_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.
unpublish_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 →