AI agents call sg_formations_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 compares historical or aggregate business formation statistics from Singapore government datasets (likely from ACRA data). It performs read-only analysis on public business data without creating, modifying, deleting, or executing any operations. The comparison of counts is a passive analytical operation with no side effects.
From the tool's definition Tool name 'sg_formations_compare' and description 'Compare business formation counts across multiple industries' indicate data retrieval and comparison only. No modification, deletion, execution, or financial operations are performed.
Attacks that exploit this kind of access
Compare business formation counts across multiple industries. 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_formations_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_formations_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_formations_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_formations_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_formations_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 →