AI agents call portal_guide 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.
In the context of a public data and business setup guidance server, 'portal_guide' most likely retrieves or presents guidance information (a read operation with no side effects). Without a description, confidence is moderate; however, the pattern of sibling tools and server purpose strongly suggest this is informational retrieval rather than state-modifying or destructive action.
From the tool's definition Tool name 'portal_guide' suggests guidance or informational retrieval. The server provides 'public data' and 'curated business setup knowledge.' Sibling tools like 'attestation_guide', 'aml_requirements', and 'analyze_setup_decision' are all…
Attacks that exploit this kind of access
portal_guide. 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 portal_guide: 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.
portal_guide 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 portal_guide 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 portal_guide. 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.
portal_guide 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 →