list_trash
AI agents call list_trash to retrieve information from Outline MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'list_trash' indicates a read-only operation that enumerates deleted or archived documents. No description is provided, which introduces some uncertainty, but the naming strongly suggests data retrieval rather than modification. The presence of separate destructive operations (batch_delete_documents) on the same server suggests this is a non-mutating query.
From the tool's definition Tool named 'list_trash' with empty description. Based on naming convention and sibling tools (archive, delete, move operations exist as separate tools), 'list_trash' most likely retrieves or queries a list of deleted/archived documents without modifying state.
Attacks that exploit this kind of access
list_trash. It is categorised as a Read tool in the Outline MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Outline MCP Server 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 Outline MCP Server. 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 Outline MCP Server MCP server (mcp-outline). 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 →