AI agents call list_saved_pictures to retrieve information from So Dsc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only enumerates files in a directory (downloads/) and returns metadata about saved pictures. It performs no modifications, deletions, or external operations. The primary risk is information disclosure of filenames and metadata, which is low severity in most contexts. The incomplete description ('These are') suggests it simply returns a listing, further confirming its read-only nature.
From the tool's definition Tool name is 'list_saved_pictures' and description states it 'List pictures saved on the host'. The verb 'list' is a read-only operation that retrieves or queries data without modification.
Attacks that exploit this kind of access
List pictures saved on the host (downloads/ directory). These are. It is categorised as a Read tool in the So Dsc MCP Server, which means it retrieves data without modifying state.
Register the So Dsc MCP server in PolicyLayer and add a rule for list_saved_pictures: 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 So Dsc. Nothing to install.
list_saved_pictures 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_saved_pictures 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_saved_pictures. 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_saved_pictures is provided by the So Dsc MCP server (nananek/so-dsc). 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 →