AI agents call makani_reverse_geocode 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.
Reverse geocoding is a standard location data lookup service. It retrieves address information from geographic coordinates without modifying, executing, or destroying anything. This is classified as Read. Severity is low because misuse would only expose publicly available address mappings, not compromise systems or cause financial harm.
From the tool's definition Tool name 'makani_reverse_geocode' indicates reverse geocoding lookup (converting coordinates to addresses). Makani is Dubai's address system. The 'reverse_geocode' operation is inherently a data retrieval function with no side effects.
Attacks that exploit this kind of access
makani_reverse_geocode. 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 makani_reverse_geocode: 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.
makani_reverse_geocode 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 makani_reverse_geocode 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 makani_reverse_geocode. 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.
makani_reverse_geocode 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 →