AI agents call osm_search_poi 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.
OSM POI searches retrieve geographic and location data without modification or side effects. This is a classic Read operation—it queries and returns public geographic data. The low confidence reflects the empty description; if the tool actually permits writes to OpenStreetMap or executes external operations, the category should be reconsidered, but the name and context strongly suggest data retrieval only.
From the tool's definition Tool name 'osm_search_poi' suggests Open Street Map point-of-interest search functionality. Context indicates the server provides public data access (prayer times, exchange rates, school ratings, air quality, business setup information).
Attacks that exploit this kind of access
osm_search_poi. 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 osm_search_poi: 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.
osm_search_poi 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 osm_search_poi 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 osm_search_poi. 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.
osm_search_poi 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 →