AI agents use restore-element-from-recycle-bin to create or update resources in Mcp Dev — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Dev environment.
Although this tool interacts with deleted content, restoration is a reversible write operation rather than a destructive one. The content is recovered and becomes active again in the CMS, making this a Write action.
From the tool's definition Tool name is 'restore-element-from-recycle-bin' with description 'Restores an element from the recycle bin.' The action restores (undeletes) data that was previously removed, reversing a destructive action.
Attacks that exploit this kind of access
Restores an element from the recycle bin. It is categorised as a Write tool in the Mcp Dev MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Dev MCP server in PolicyLayer and add a rule for restore-element-from-recycle-bin: 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 Mcp Dev. Nothing to install.
restore-element-from-recycle-bin 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 restore-element-from-recycle-bin 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 restore-element-from-recycle-bin. 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.
restore-element-from-recycle-bin is provided by the Mcp Dev MCP server (@umbraco-cms/mcp-dev). 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 →