AI agents call list_trash to retrieve information from Ai Brain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about soft-deleted (recoverable) documents. It performs a passive query with no side effects—it neither modifies, executes operations, nor irreversibly deletes data. The ability to view trash contents is essential for recovery workflows and poses minimal risk if invoked by an AI agent, as it only exposes metadata about deleted items.
From the tool's definition Tool name 'list_trash' and description 'List soft-deleted documents' indicate data retrieval only. The verb 'list' is a read operation that queries the state of deleted documents without modifying or removing them.
Attacks that exploit this kind of access
List soft-deleted documents in a space that can still be restored or purged. It is categorised as a Read tool in the Ai Brain MCP Server, which means it retrieves data without modifying state.
Register the Ai Brain MCP server in PolicyLayer and add a rule for list_trash: 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 Ai Brain. Nothing to install.
list_trash is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_trash 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 list_trash. 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.
list_trash is provided by the Ai Brain MCP server (thejoshgriffith/ai-brain). 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 →