AI agents call bank_recommendation 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.
Without a description, confidence is moderate. The tool name and server context suggest Read (retrieval of bank recommendation data for business setup guidance), not Write or Execute. No evidence of side effects, code execution, data modification, deletion, or financial transactions. Classified as Read with low severity due to its informational nature in a public-data-focused server.
From the tool's definition Tool name 'bank_recommendation' suggests retrieval of banking information. The empty description is uninformative; however, sibling tools like 'bank_details' and 'aml_requirements' indicate this server provides public/reference data rather than transactional…
Attacks that exploit this kind of access
bank_recommendation. 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 bank_recommendation: 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.
bank_recommendation 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 bank_recommendation 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 bank_recommendation. 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.
bank_recommendation 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 →