AI agents call list_root_paths to retrieve information from Mcp Base without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a non-destructive query that retrieves filesystem path configuration. It reads and returns existing data without modifying, deleting, or executing anything. The blast radius of misuse is minimal (at worst, an attacker learns what paths are available), making severity low.
From the tool's definition Tool name and description indicate it 'Return[s] the configured root paths' — a retrieval operation with no side effects. Returns configuration data only.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Return the configured root paths available for filesystem listing. It is categorised as a Read tool in the Mcp Base MCP Server, which means it retrieves data without modifying state.
Register the Mcp Base MCP server in PolicyLayer and add a rule for list_root_paths: 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 Mcp Base. Nothing to install.
list_root_paths 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_root_paths 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_root_paths. 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_root_paths is provided by the Mcp Base MCP server (sesopenko/mcp-filesystem-readonly). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
list_root_paths is one line of Mcp Base's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →