AI agents call list_plan_categories to retrieve information from MCP-Dubai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists pre-defined plan categories from the MCP-Dubai server. It performs a simple data retrieval operation analogous to a list or fetch call. There is no modification, deletion, execution, or financial impact. The blast radius of misuse is minimal—an agent could only retrieve categorical metadata about data analyst plans. Classification as Read is appropriate.
From the tool's definition Tool name 'list_plan_categories' and description 'List the available data_analyst plan categories' indicate a retrieval operation that queries and returns categorical data with no side effects.
Attacks that exploit this kind of access
List the available data_analyst plan categories. It is categorised as a Read tool in the MCP-Dubai MCP Server, which means it retrieves data without modifying state.
Register the MCP-Dubai MCP server in PolicyLayer and add a rule for list_plan_categories: 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-Dubai. Nothing to install.
list_plan_categories 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_plan_categories 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_plan_categories. 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_plan_categories is provided by the MCP-Dubai MCP server (mahdi-salmanzade/mcp-dubai). 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 →