AI agents call sg_psi 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 is a read-only data retrieval tool that queries environmental monitoring data. Categorized as Read because it retrieves/queries data with no side effects. Severity is high due to potential for misuse: an agent could systematically gather PSI data to trigger false environmental alerts, manipulate public health decision-making, or coordinate harmful actions based on air quality patterns.
From the tool's definition Tool returns live Pollutant Standards Index (PSI) data from Singapore's National Environment Agency (NEA). Description states 'Returns the' (incomplete but clearly a data retrieval function). No modification, deletion, or execution capabilities indicated.
Attacks that exploit this kind of access
Live NEA Pollutant Standards Index (PSI) for Singapore. Returns the. 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_psi: 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_psi 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_psi 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_psi. 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_psi 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 →