AI agents call sg_acra_search_entities 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 or queries publicly available corporate registry data from Singapore's ACRA (Accounting and Corporate Regulatory Authority) database. The use of 'search' indicates a read-only operation with no side effects. Even if misused by an AI agent, it can only fetch existing public corporate information, posing minimal risk. The server-side filtering does not change the Read classification.
From the tool's definition Tool name contains 'search' and description states 'Search the curated ACRA corporate registry' - a query operation with no modification or deletion capability.
Attacks that exploit this kind of access
Search the curated ACRA corporate registry resource server-side. 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_acra_search_entities: 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_acra_search_entities 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_acra_search_entities 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_acra_search_entities. 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_acra_search_entities 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 →