AI agents call search_saiketsu to retrieve information from Tax Law without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries publicly available tax tribunal ruling examples without modifying, executing code, deleting, or creating financial transactions. The description confirms it is a search operation that returns matching records from an official Japanese tax law database. There are no side effects or irreversible changes involved.
From the tool's definition The tool name is 'search_saiketsu' and the description states it searches keyword in tax tribunal ruling examples ('国税不服審判所の公表裁決事例をキーワードで検索する'), targeting summary text and category names ('要旨テキストとカテゴリ名を対象に検索').
Attacks that exploit this kind of access
国税不服審判所の公表裁決事例をキーワードで検索する。要旨テキストとカテゴリ名を対象に検索。スペース区切りでAND検索。初回は事例集目次の取得に時間がかかる（以降はキャッシュ）。. It is categorised as a Read tool in the Tax Law MCP Server, which means it retrieves data without modifying state.
Register the Tax Law MCP server in PolicyLayer and add a rule for search_saiketsu: 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 Tax Law. Nothing to install.
search_saiketsu 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_saiketsu 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_saiketsu. 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_saiketsu is provided by the Tax Law MCP server (xqzimgz/tax-law-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 →