AI agents call dld_search_transactions 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.
The DLD (Dubai Land Department) maintains public property and transaction records. A search function on a public data server most likely retrieves historical transaction information without modifying it. The Read category applies unless the tool can delete or modify records, which is unlikely given the server's stated purpose (providing public data and business setup knowledge).
From the tool's definition Tool name 'dld_search_transactions' suggests querying Dubai Land Department transaction records. The 'search' verb and context (public data server with prayer times, exchange rates, school ratings) indicate data retrieval.
Attacks that exploit this kind of access
dld_search_transactions. 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 dld_search_transactions: 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.
dld_search_transactions 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 dld_search_transactions 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 dld_search_transactions. 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.
dld_search_transactions 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 →