AI agents call rta_salik_tariff 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 appears to retrieve tariff/pricing information for Salik (Dubai's toll system), which is a read-only data lookup with no side effects. It would allow agents to query public toll rates, not modify them or trigger payments. Lack of description lowers confidence slightly, but the server's stated focus on providing 'public data' and the tool's naming convention support a Read classification.
From the tool's definition Tool name 'rta_salik_tariff' indicates retrieval of RTA (Roads and Transport Authority) Salik tariff information. The server context provides 'public data' including exchange rates and other informational queries.
Attacks that exploit this kind of access
rta_salik_tariff. 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 rta_salik_tariff: 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.
rta_salik_tariff 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 rta_salik_tariff 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 rta_salik_tariff. 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.
rta_salik_tariff 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 →