AI agents call sg_coe_history 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 historical Certificate of Entitlement (COE) premium data from a Singapore government database. It has no capability to modify, delete, or execute operations. The blast radius of misuse is minimal - an agent could only retrieve publicly available historical pricing information, which poses no security, financial, or operational risk.
From the tool's definition Tool retrieves 'COE premium time series for a single vehicle category' - a historical data query with no modification or side effects. The verb 'time series' and context of retrieving government data (data.gov.sg) indicates a read-only retrieval operation.
Attacks that exploit this kind of access
COE premium time series for a single vehicle category. 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_history: 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_history 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_history 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_history. 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_history 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 →