AI agents call qfzp_check 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 performs a lookup or eligibility check against QFZP (likely a Dubai/UAE free zone program) criteria. It reads and returns eligibility information based on input parameters, with no indication of data modification, deletion, financial transactions, or external command execution. It is purely informational, consistent with other Read-category tools on this server like 'accelerator_search' and 'bank_details'.
From the tool's definition Tool name 'qfzp_check' and description 'Check QFZP eligibility for a free zone business' indicate a query/lookup operation that retrieves eligibility status without modifying data, creating side effects, or executing arbitrary operations.
Attacks that exploit this kind of access
Check QFZP eligibility for a free zone business. 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 qfzp_check: 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.
qfzp_check 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 qfzp_check 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 qfzp_check. 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.
qfzp_check 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 →