Publish a resource (product, collection, page) to a sales channel.
AI agents use publish_resource to create or update resources in AdminAgent — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AdminAgent environment.
Publishing a product, collection, or page to a sales channel is a reversible write operation that modifies the visibility and accessibility of store resources. It creates or updates the published state of these resources but does not irreversibly delete data (Destructive), does not transfer money (Financial), does not execute arbitrary code (Execute), and is more than passive retrieval (Read).
From the tool's definition Tool description: 'Publish a resource (product, collection, page) to a sales channel.' The word 'Publish' indicates a state change that makes resources publicly visible and available for sale.
Attacks that exploit this kind of access
Publish a resource (product, collection, page) to a sales channel. It is categorised as a Write tool in the AdminAgent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AdminAgent MCP server in PolicyLayer and add a rule for publish_resource: 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 AdminAgent. Nothing to install.
publish_resource 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_resource 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_resource. 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_resource is provided by the AdminAgent MCP server (rushikeshmore/admin-agent). 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 →