AI agents call fnd 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 tool retrieves historical or predictive weather data from the Hong Kong Observatory. It performs a simple read-only query operation. There is no data modification, deletion, code execution, financial transaction, or irreversible action. The low severity reflects minimal blast radius—misuse would only return incorrect weather information to an end-user, with no operational or financial consequences.
From the tool's definition Tool name 'fnd' described as '9-day Weather Forecast API Request' with parameters for language selection. This is a retrieval operation that queries weather forecast data with no side effects, modifications, or external actions triggered.
Attacks that exploit this kind of access
9-day Weather Forecast (fnd) 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 fnd: 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.
fnd 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 fnd 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 fnd. 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.
fnd 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 →