AI agents call aml_requirements 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 presents Anti-Money Laundering/Countering Financing of Terrorism (AML/CFT) compliance information for business categories in Dubai/UAE. It is purely informational—returning regulatory requirements or guidelines to help entrepreneurs understand their compliance obligations. There is no capability to modify data, execute operations, delete records, or move money.
From the tool's definition Tool name 'aml_requirements' and description 'Return AML/CFT requirements for a business category' indicate retrieval of informational requirements/guidelines. Uses verb 'Return' (not 'Create', 'Modify', 'Execute', or 'Delete').
Attacks that exploit this kind of access
Return AML/CFT requirements for a business category. 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 aml_requirements: 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.
aml_requirements 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 aml_requirements 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 aml_requirements. 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.
aml_requirements 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 →