AI agents call khda_search_school 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 public school information from a UAE authority database. It performs no modifications, deletions, or executions. The search pattern and server context indicate data retrieval with no side effects. Confidence is slightly reduced (0.85 vs 1.0) due to empty description, but the tool name and context strongly suggest Read classification.
From the tool's definition Tool name 'khda_search_school' indicates a search operation against KHDA (Knowledge and Human Development Authority) data. In the context of public data access described in the server purpose ('school ratings'), this is a retrieval-only operation.
Attacks that exploit this kind of access
khda_search_school. 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 khda_search_school: 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.
khda_search_school 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 khda_search_school 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 khda_search_school. 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.
khda_search_school 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 →