AI agents call get_meeting_record 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 data from the NDL Kokkai API without any side effects. It fetches a pre-existing committee meeting transcript record using an identifier. No data is created, modified, deleted, or executed—only retrieved. This is a standard read operation with minimal blast radius if misused (returning unwanted but non-damaging public records).
From the tool's definition Tool description states 'Retrieve the full transcript' and 'via the NDL Kokkai API' - explicit read operation with no modification, deletion, or execution capability. issueID is a query parameter used to fetch existing data.
Attacks that exploit this kind of access
Retrieve the full transcript of one Diet committee meeting by issueID via the NDL Kokkai API. Use the issueID from a find_diet_qa result. 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 get_meeting_record: 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.
get_meeting_record 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_meeting_record 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_meeting_record. 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_meeting_record 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 →