AI agents call find_diet_qa 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 retrieves and queries historical Japanese Diet committee Q&A records from the NDL Kokkai API without any side effects. It only searches and returns data (speeches, speaker information, committee details, and URLs). There is no capability to create, modify, delete, or execute operations. The search functionality is purely informational.
From the tool's definition Tool performs 'full-text search' and 'returns speeches' with metadata; no modification, deletion, or execution capability mentioned.
Attacks that exploit this kind of access
Full-text search of Japanese Diet committee speeches via the NDL Kokkai API. Returns speeches matching the keyword along with speaker, position, committee, and the canonical NDL URL. 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 find_diet_qa: 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.
find_diet_qa 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 find_diet_qa 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 find_diet_qa. 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.
find_diet_qa 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 →