Unpublish an asset or multiple assets. Accepts either a single assetId (string) or an array of assetIds (up to 100 assets). For a single asset, it uses the standard unpublish operation. For multiple assets, it automatically uses bulk unpublishing.
AI agents use unpublish_asset to create or update resources in Contentful MCP Remote Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Contentful MCP Remote Server environment.
Unpublishing reverses a published state, making assets unavailable publicly, but it is reversible (assets can be re-published). This is a state modification rather than deletion or irreversible destruction. However, the blast radius is high since it can affect up to 100 assets at once, potentially taking significant content offline. It falls under Write as the operation can be undone by re-publishing.
From the tool's definition Unpublish an asset or multiple assets... uses the standard unpublish operation... bulk unpublishing
Attacks that exploit this kind of access
Unpublish an asset or multiple assets. Accepts either a single assetId (string) or an array of assetIds (up to 100 assets). For a single asset, it uses the standard unpublish operation. For multiple assets, it automatically uses bulk unpublishing. It is categorised as a Write tool in the Contentful MCP Remote Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Contentful MCP Remote Server MCP server in PolicyLayer and add a rule for unpublish_asset: 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 Contentful MCP Remote Server. Nothing to install.
unpublish_asset 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_asset 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_asset. 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_asset is provided by the Contentful MCP Remote Server MCP server (renzoqcad/contentful-express-mcp-server). 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 →