AI agents call sg_dengue_clusters 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 fetches public health surveillance data without side effects. It returns information about dengue clusters maintained by Singapore's health authorities. There is no capability to modify, delete, or execute operations. The data is read-only public health information. Severity is low because dengue cluster information is already public and widely disseminated; unauthorized access poses minimal risk.
From the tool's definition Tool description indicates 'Active NEA dengue clusters in Singapore (live)' - retrieves current dengue cluster data from the National Environment Agency. The tool name and description use no action verbs suggesting modification, deletion, or execution.
Attacks that exploit this kind of access
Active NEA dengue clusters in Singapore (live). The legacy realtime. 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_dengue_clusters: 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_dengue_clusters 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_dengue_clusters 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_dengue_clusters. 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_dengue_clusters 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 →