AI agents call search_videos to retrieve information from Mcp Chzzk without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries VOD metadata based on titles and tags. It performs a search operation that does not modify, delete, or execute external operations. There is no capability to create, modify, or destroy data. The search scope is limited to already-recorded video content on the Chzzk platform. This is a straightforward read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool description: 'Search Chzzk VOD (recorded videos) by VIDEO TITLE / tags.' The verb 'search' combined with the explicit statement that it queries recorded videos (VODs) indicates data retrieval with no side effects.
Attacks that exploit this kind of access
Search Chzzk VOD (recorded videos) by VIDEO TITLE / tags. Does NOT search live broadcasts — use. It is categorised as a Read tool in the Mcp Chzzk MCP Server, which means it retrieves data without modifying state.
Register the Mcp Chzzk MCP server in PolicyLayer and add a rule for search_videos: 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 Mcp Chzzk. Nothing to install.
search_videos 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_videos 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_videos. 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_videos is provided by the Mcp Chzzk MCP server (saya6k/mcp-chzzk). 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 →