list_ivods
AI agents call list_ivods to retrieve information from Taiwan Legislative Yuan MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or lists IVOD recordings from Taiwan's Legislative Yuan—a read-only query operation with no side effects, modification capabilities, or execution risks. The legislative data is public record. Even with an empty description, the naming convention ('list_') and server context strongly suggest a safe Read operation. Confidence is reduced slightly due to missing description, but the pattern is clear.
From the tool's definition Tool name 'list_ivods' indicates a listing/retrieval operation. IVOD refers to Internet Video-on-Demand recordings of legislative sessions.
Attacks that exploit this kind of access
list_ivods. It is categorised as a Read tool in the Taiwan Legislative Yuan MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Taiwan Legislative Yuan MCP Server MCP server in PolicyLayer and add a rule for list_ivods: 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 Taiwan Legislative Yuan MCP Server. Nothing to install.
list_ivods 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 list_ivods 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 list_ivods. 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.
list_ivods is provided by the Taiwan Legislative Yuan MCP Server MCP server (narumiruna/ly-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 →