AI agents call sg_crime_compare 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 and ranks historical crime data by type and count—a pure read operation with no side effects. It queries public government statistics without creating, modifying, deleting, or executing anything. The blast radius of misuse is negligible; an agent could only abuse it by requesting data repeatedly or using it for unintended analysis, but the tool itself cannot alter state or cause harm.
From the tool's definition Tool name 'sg_crime_compare' and description 'Rank all crime types by case count for a given year. Returns' indicate a data retrieval operation that queries crime statistics from Singapore government datasets (data.gov.sg).
Attacks that exploit this kind of access
Rank all crime types by case count for a given year. Returns. 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_crime_compare: 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_crime_compare 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_crime_compare 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_crime_compare. 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_crime_compare 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 →