AI agents call sg_air_quality to retrieve information from Sg Data without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns environmental monitoring data from Singapore's data.gov.sg platform. It has no side effects, cannot modify state, and poses minimal risk if misused by an AI agent—worst case being irrelevant or alarming air quality reports. No financial, destructive, or code execution consequences. Classified as Read with low severity and high confidence.
From the tool's definition Tool retrieves 'real-time PSI and PM2.5 air quality readings' with no modification, creation, or deletion of data. The verb 'Get' and context 'Use for haze conditions and health advisories' indicate passive information retrieval.
Attacks that exploit this kind of access
Get Singapore real-time PSI and PM2.5 air quality readings by region. Use for haze conditions and health advisories. It is categorised as a Read tool in the Sg Data MCP Server, which means it retrieves data without modifying state.
Register the Sg Data MCP server in PolicyLayer and add a rule for sg_air_quality: 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 Sg Data. Nothing to install.
sg_air_quality 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_air_quality 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_air_quality. 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_air_quality is provided by the Sg Data MCP server (vdineshk/sg-data-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 →