AI agents call sg_moe_schools_near 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 performs a read-only query against a dataset of Singapore schools, filtering results by postal code prefix. It retrieves information without side effects. The severity is low as the data being accessed (school locations and postal codes) is already public government information, and the tool has no capability to modify, delete, or execute arbitrary operations.
From the tool's definition Tool description states 'Find schools whose postal_code shares a prefix with the supplied' - this is a search/query operation that retrieves school location data based on postal code matching.
Attacks that exploit this kind of access
Find schools whose postal_code shares a prefix with the supplied. 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_moe_schools_near: 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_moe_schools_near 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_moe_schools_near 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_moe_schools_near. 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_moe_schools_near 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 →