AI agents call sg_divorces 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 public divorce statistics from Singapore government data sources (data.gov.sg). It is a read-only query operation that returns aggregated statistical information. There is no indication of write, execute, destructive, or financial operations. The incomplete description ('Defaults to total divorces &') is consistent with a simple data retrieval tool.
From the tool's definition Tool name 'sg_divorces' and description 'Singapore divorce statistics' indicate retrieval of historical/statistical data with no capability to modify, delete, or execute external operations.
Attacks that exploit this kind of access
Singapore divorce statistics. Defaults to total divorces &. 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_divorces: 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_divorces 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_divorces 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_divorces. 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_divorces 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 →