検索インデックスの統計情報を取得します。
AI agents call get_index_stats to retrieve information from Japan Ir Search without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a data retrieval operation on index metadata. It has no side effects, cannot modify state, execute code, or affect financial data. The minimal blast radius from misuse is limited to information disclosure of non-sensitive index statistics (document count, index size, etc.). This is a straightforward Read category tool with low severity.
From the tool's definition Tool retrieves index statistics (検索インデックスの統計情報を取得します - 'get index statistics'). This is a read-only operation that queries metadata about the search index without modifying, executing, or deleting any data.
Attacks that exploit this kind of access
検索インデックスの統計情報を取得します。. It is categorised as a Read tool in the Japan Ir Search MCP Server, which means it retrieves data without modifying state.
Register the Japan Ir Search MCP server in PolicyLayer and add a rule for get_index_stats: 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 Japan Ir Search. Nothing to install.
get_index_stats 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_index_stats 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_index_stats. 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_index_stats is provided by the Japan Ir Search MCP server (tamcho113/japan-ir-search). 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 →