AI agents call sg_coe_demand_supply 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 returns calculated demand-supply metrics from Singapore government datasets. It performs no side effects, creates no data, executes no code, deletes nothing, and involves no financial transactions. It is a simple data retrieval operation typical of a government data API endpoint.
From the tool's definition Tool name 'sg_coe_demand_supply' and description indicate it retrieves COE (Certificate of Entitlement) oversubscription ratio data by calculating bids_received / quota.
Attacks that exploit this kind of access
COE oversubscription ratio (bids_received / quota) for a single. 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_coe_demand_supply: 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_coe_demand_supply 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_coe_demand_supply 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_coe_demand_supply. 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_coe_demand_supply 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 →