AI agents call search_bills to retrieve information from Houan without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries public legislative data from the NDL Kokkai API and returns metadata and URLs. It retrieves information without creating, modifying, deleting, or executing any operations. The lack of side effects and purely informational nature places it squarely in the Read category with low severity, as misuse would only result in accessing publicly available information.
From the tool's definition Tool description indicates it "Search[es]... bills" and "Returns bill metadata with proceedings and full-text URLs." These are read-only retrieval operations with no mutation, deletion, or execution of code.
Attacks that exploit this kind of access
Search current-session Japanese Diet bills (衆議院議案情報 / 参議院議案情報) by title keyword. Returns bill metadata with proceedings and full-text URLs. It is categorised as a Read tool in the Houan MCP Server, which means it retrieves data without modifying state.
Register the Houan MCP server in PolicyLayer and add a rule for search_bills: 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 Houan. Nothing to install.
search_bills 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_bills 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_bills. 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_bills is provided by the Houan MCP server (shayouworld/houan-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 →