Get all AMeDAS stations of a specific type.
AI agents call get_stations_of_type to retrieve information from JMA Data MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a pure data retrieval operation querying station metadata from the JMA database. It returns information about meteorological stations based on type filtering. There is no capability to modify, delete, or execute operations on the underlying data or external systems. The blast radius of misuse is minimal — an agent could only retrieve publicly available station information.
From the tool's definition Tool name is 'get_stations_of_type' and description states it 'Get all AMeDAS stations of a specific type' — this retrieves/queries metadata about weather stations with no side effects or data modification.
Attacks that exploit this kind of access
Get all AMeDAS stations of a specific type. It is categorised as a Read tool in the JMA Data MCP MCP Server, which means it retrieves data without modifying state.
Register the JMA Data MCP server in PolicyLayer and add a rule for get_stations_of_type: 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 JMA Data MCP. Nothing to install.
get_stations_of_type 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 get_stations_of_type 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 get_stations_of_type. 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.
get_stations_of_type is provided by the JMA Data MCP server (koizumikento/jma-data-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 →