AI agents call sg_cpi_history 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 queries and retrieves historical Consumer Price Index (CPI) data from Singapore government datasets. It performs a simple lookup/filter operation on existing data with no side effects, no code execution, no data modification, and no destructive capabilities. The substring matching is a standard read filter. This is a straightforward data retrieval tool appropriate for informational purposes only.
From the tool's definition Tool name and description indicate it retrieves 'Monthly CPI time series' — a historical query operation with no modification or execution capability. The description mentions 'substring match' for filtering, consistent with read-only data retrieval.
Attacks that exploit this kind of access
Monthly CPI time series for a single sub-index (substring match. 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_cpi_history: 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_cpi_history 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_cpi_history 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_cpi_history. 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_cpi_history 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 →