AI agents call list_downloads to retrieve information from Wraith without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'list_' prefix and downloads context indicate this tool queries or enumerates downloaded files without modifying, deleting, or executing operations. While the server has concerning capabilities (bot detection bypass, stealth browsing), this specific tool appears limited to informational retrieval. Classified as Read with low severity due to minimal blast radius from misuse.
From the tool's definition Tool name 'list_downloads' indicates a retrieval operation with no side effects. The 'list' prefix is characteristic of Read category tools (compare to 'list_sessions' on the same server).
Attacks that exploit this kind of access
list_downloads. It is categorised as a Read tool in the Wraith MCP Server, which means it retrieves data without modifying state.
Register the Wraith MCP server in PolicyLayer and add a rule for list_downloads: 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 Wraith. Nothing to install.
list_downloads 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_downloads 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_downloads. 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_downloads is provided by the Wraith MCP server (koreahwan/wraith-mcp). 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 →