AI agents call fcsc_search_dataset 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 tool is named 'fcsc_search_dataset' which indicates a search/query function. Given the server context (public data access for entrepreneurs) and the absence of any descriptive indication of mutation, deletion, or financial operations, this is classified as Read.
From the tool's definition Tool name 'fcsc_search_dataset' suggests a search operation over a dataset, consistent with the server's purpose of providing 'access to Dubai and UAE public data.' The name pattern (search + dataset) and sibling tools (accelerator_search, air_quality_dubai,…
Attacks that exploit this kind of access
fcsc_search_dataset. 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 fcsc_search_dataset: 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.
fcsc_search_dataset 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 fcsc_search_dataset 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 fcsc_search_dataset. 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.
fcsc_search_dataset 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 →