AI agents call get_law 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 queries and retrieves read-only data from an official Japanese legal database. It accepts queries (potentially with abbreviated law names) and returns matching provisions. There are no side effects, no data modification, no code execution, and no destructive operations. The low severity reflects that retrieving public legal information poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'get_law' and description explicitly state retrieval of specific provisions from Japanese law (「特定の条文を取得する」= 'retrieve specific provisions'). Uses e-Gov legal API v2. No modification, deletion, or execution capabilities mentioned.
Attacks that exploit this kind of access
日本の法令から特定の条文を取得する。e-Gov法令API v2を使用。略称にも対応（所法→所得税法、措法→租税特別措置法 等）。. 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 get_law: 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.
get_law 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_law 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_law. 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_law 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 →