AI agents call rta_search_metro_stations 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.
Search tools that query public transit information are read-only operations with no data modification, execution, or destructive capabilities. The empty description lowers confidence slightly, but the tool name and server context (public data access) strongly indicate this retrieves metro station information without side effects.
From the tool's definition Tool name 'rta_search_metro_stations' indicates a search/query operation against RTA (Roads and Transport Authority) metro station data. The naming pattern ('search') and context of a Dubai public data server suggest data retrieval with no side effects.
Attacks that exploit this kind of access
rta_search_metro_stations. 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_search_metro_stations: 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_search_metro_stations 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_search_metro_stations 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_search_metro_stations. 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_search_metro_stations 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 →