AI agents call list_allowed_directories to retrieve information from Graphics without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries configuration or state to discover which directories are accessible. It has no side effects, does not execute code, does not modify data, and does not delete anything. The low severity reflects that disclosure of directory paths poses minimal risk even if misused, as it merely informs rather than enables direct harm.
From the tool's definition Tool name is 'list_allowed_directories' and description states 'List directories where file operations are allowed' — it retrieves information about permitted paths with no modification or execution of operations.
Attacks that exploit this kind of access
List directories where file operations are allowed. It is categorised as a Read tool in the Graphics MCP Server, which means it retrieves data without modifying state.
Register the Graphics MCP server in PolicyLayer and add a rule for list_allowed_directories: 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 Graphics. Nothing to install.
list_allowed_directories 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_allowed_directories 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_allowed_directories. 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_allowed_directories is provided by the Graphics MCP server (lesleslie/graphics-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 →