AI agents call sg_fx_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 financial market data (exchange rates) without the ability to execute trades, modify records, delete data, or trigger external operations. It is purely informational/analytical in nature, presenting only past rate information. The low severity reflects minimal risk even if misused, as historical data retrieval alone cannot directly harm systems or cause financial loss.
From the tool's definition Tool name 'sg_fx_history' and description 'Monthly SGD rate time series for a single currency. Returns' indicate retrieval of historical foreign exchange rate data. No modification, deletion, execution, or financial transaction capability is present.
Attacks that exploit this kind of access
Monthly SGD rate time series for a single currency. Returns. 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_fx_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_fx_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_fx_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_fx_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_fx_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 →