AI agents call dfm_index 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 financial market index data without the ability to modify, execute transactions, or delete information. It is a read-only query of publicly available Dubai Financial Market index information. While it relates to financial data, it does not move money, commit financial obligations, or enable trading—it merely reports current index values.
From the tool's definition Tool provides a 'snapshot' and 'intraday summary' of the DFM General Index with no write, execute, or destructive capabilities indicated. The description explicitly states '(no key)', suggesting read-only access to public market data.
Attacks that exploit this kind of access
Latest DFM General Index snapshot with an intraday summary (no key). 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 dfm_index: 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.
dfm_index 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 dfm_index 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 dfm_index. 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.
dfm_index 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 →