AI agents call sg_hdb_resale_search 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 filters public HDB resale transaction records from Singapore's public datasets. It performs a read-only search operation with no side effects, no code execution, and no data modification capabilities. The data appears to be historical public records (Jan 2017+), making this a straightforward data retrieval function with minimal blast radius if misused.
From the tool's definition Tool name 'sg_hdb_resale_search' and description 'Search HDB resale flat transactions' indicate query/retrieval of historical public transaction data with filters (town). No modification, deletion, or execution of external systems.
Attacks that exploit this kind of access
Search HDB resale flat transactions (Jan 2017+). Filters: town,. 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_hdb_resale_search: 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_hdb_resale_search 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_hdb_resale_search 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_hdb_resale_search. 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_hdb_resale_search 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 →