AI agents call dld_search_rent_contracts 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 queries existing rental contract information from Dubai's Land Department (DLD) database without modifying, deleting, or executing actions. It has no side effects and poses minimal risk—typical blast radius is information disclosure of already-public property records. The data accessed (Ejari contracts) is public registration data in Dubai.
From the tool's definition Tool name contains 'search' and description states 'Search DLD rent contracts', indicating a query/retrieval operation on publicly available Ejari rental contract data via Dubai Pulse.
Attacks that exploit this kind of access
Search DLD rent contracts (Ejari data) via Dubai Pulse. 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_rent_contracts: 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_rent_contracts 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_rent_contracts 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_rent_contracts. 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_rent_contracts 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 →