AI agents call warnsum to retrieve information from Mcp Hko without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward data retrieval tool that queries the Hong Kong Observatory's weather warning summary API. It has no side effects, does not modify data, does not execute arbitrary code, and does not involve financial transactions. It simply fetches and returns weather warning information, making it a Read category tool with low severity risk.
From the tool's definition Tool name 'warnsum' (Weather Warning Summary) and description indicate it retrieves weather warning information via API request. The parameter structure (lang for language selection) suggests a query/retrieval operation with no data modification capabilities.
Attacks that exploit this kind of access
Weather Warning Summary (warnsum) API Request Parameters: - lang:. It is categorised as a Read tool in the Mcp Hko MCP Server, which means it retrieves data without modifying state.
Register the Mcp Hko MCP server in PolicyLayer and add a rule for warnsum: 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 Mcp Hko. Nothing to install.
warnsum 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 warnsum 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 warnsum. 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.
warnsum is provided by the Mcp Hko MCP server (louiscklaw/mcp-hko). 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 →