AI agents call search_lives 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 queries and retrieves information about live broadcasts without modifying, deleting, or executing any operations. It performs a read-only search against broadcast metadata. There are no financial implications, no code execution, and no data modification.
From the tool's definition Tool description explicitly states 'Search currently live Chzzk broadcasts' and the verb 'search' indicates data retrieval.
Attacks that exploit this kind of access
Search currently live Chzzk broadcasts by LIVE TITLE (the title the streamer set for this broadcast — NOT the channel name). If you want to find a specific streamer by handle, 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_lives: 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_lives 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_lives 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_lives. 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_lives 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 →