AI agents call sg_coe_latest 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 historical or current COE bidding results from a public government dataset. It performs a simple data lookup/query operation with no side effects, no code execution, no data modification, and no financial transactions. The action is read-only, consistent with tools like 'get' or 'fetch'.
From the tool's definition Tool name 'sg_coe_latest' and description 'Get the most recent COE bidding result per vehicle category' indicate a retrieval operation that queries Singapore government data (Certificate of Entitlement bidding results) with no modification, deletion, or…
Attacks that exploit this kind of access
Get the most recent COE bidding result per vehicle category. If. 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_latest: 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_latest 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_latest 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_latest. 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_latest 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 →