Search AMeDAS stations by name (Japanese, Kana, or English).
AI agents call search_stations 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 is a straightforward read-only operation that retrieves station information from the JMA database. It performs a search query with no side effects, no data modification, and no irreversible actions. The blast radius of misuse is negligible—an agent querying station names cannot harm systems or data. Low severity is appropriate for informational queries on public weather data.
From the tool's definition The tool 'search_stations' queries AMeDAS station data by name without modifying any data. The description explicitly indicates it 'search[es]' stations, which is a retrieval operation.
Attacks that exploit this kind of access
Search AMeDAS stations by name (Japanese, Kana, or English). 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 search_stations: 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.
search_stations 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 search_stations 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 search_stations. 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.
search_stations 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 →