AI agents call list_desktop_routes to retrieve information from Nocobase without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries existing route/page/menu data from NocoBase without any side effects. It is a read-only operation that returns information about desktop routes and their types. No data is created, modified, deleted, or executed as a result of this tool's use.
From the tool's definition Tool name 'list_desktop_routes' and description explicitly states it 'List[s] all desktop routes' with no modification or deletion capabilities.
Attacks that exploit this kind of access
List all desktop routes (pages and menus) in NocoBase v2. Each route has a type:. It is categorised as a Read tool in the Nocobase MCP Server, which means it retrieves data without modifying state.
Register the Nocobase MCP server in PolicyLayer and add a rule for list_desktop_routes: 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 Nocobase. Nothing to install.
list_desktop_routes 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_desktop_routes 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_desktop_routes. 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_desktop_routes is provided by the Nocobase MCP server (puguhsudarma/nocobase-mcp-server). 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 →