AI agents call sg_retail_sales_latest to retrieve information from Sgdata without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs data retrieval (Read category) from Singapore government datasets. While the operation itself is non-destructive, the severity is elevated to 'high' because retail sales index data is economically sensitive information that could be misused by an AI agent to make unauthorized financial decisions, market manipulation, or inform trading strategies if combined with other tools or context.
From the tool's definition Tool retrieves 'most recent retail sales index value' - a query operation that returns data without modification. The name and description indicate a read-only data retrieval function.
Attacks that exploit this kind of access
Most recent retail sales index value for a matching sub-industry. It is categorised as a Read tool in the Sgdata MCP Server, which means it retrieves data without modifying state.
Register the Sgdata MCP server in PolicyLayer and add a rule for sg_retail_sales_latest: 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 Sgdata. Nothing to install.
sg_retail_sales_latest 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 sg_retail_sales_latest 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 sg_retail_sales_latest. 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.
sg_retail_sales_latest is provided by the Sgdata MCP server (sypherin/sgdata-mcp). 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 →