AI agents call sg_retail_sales_yoy 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 retrieves and queries publicly available statistical data (retail sales indices) with no capability to modify, delete, or execute external operations. It produces no side effects beyond returning requested data. The incomplete description ('for a') does not suggest any write or execute capabilities.
From the tool's definition Tool name 'sg_retail_sales_yoy' and description 'Year-on-year percent change in retail sales index' indicate a data retrieval operation that queries historical retail sales statistics from Singapore government data sources.
Attacks that exploit this kind of access
Year-on-year percent change in retail sales index for a. 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_yoy: 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_yoy 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_yoy 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_yoy. 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_yoy 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 →