法令の目次（編・章・節・条の構造）のみを取得する。トークン節約用。depth で階層を浅く打ち切れる（民法・会社法のような大規模法令の概観把握向け）。
AI agents call get_toc to retrieve information from Houki e-Gov MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only retrieval operation on Japanese law metadata (table of contents structure). It has no side effects, cannot modify or delete data, and does not execute arbitrary code or commands. The depth parameter allows filtering the hierarchy level but remains a simple data retrieval operation.
From the tool's definition get_toc retrieves the table of contents (目次) structure of laws with optional depth limiting; the description explicitly states it 'only retrieves' (のみを取得する) the TOC for 'token saving' purposes.
Attacks that exploit this kind of access
法令の目次（編・章・節・条の構造）のみを取得する。トークン節約用。depth で階層を浅く打ち切れる（民法・会社法のような大規模法令の概観把握向け）。. It is categorised as a Read tool in the Houki e-Gov MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Houki e-Gov MCP Server MCP server in PolicyLayer and add a rule for get_toc: 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 Houki e-Gov MCP Server. Nothing to install.
get_toc 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_toc 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_toc. 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_toc is provided by the Houki e-Gov MCP Server MCP server (shuji-bonji/houki-egov-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 →