AI agents call sg_fx_basket 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 foreign exchange rate information for SGD currency pairs. It performs a query operation to fetch data from Singapore government datasets (data.gov.sg) with no side effects, no data modification, and no execution of external commands. The incomplete description ('If month is') suggests a simple parameterized read operation.
From the tool's definition Tool name 'sg_fx_basket' and description 'All major SGD currency pairs for a single month' indicates retrieval of historical or current foreign exchange data without modification capabilities.
Attacks that exploit this kind of access
All major SGD currency pairs for a single month. If month is. 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_basket: 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_basket 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_basket 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_basket. 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_basket 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 →