AI agents call search_channels 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 channel information from the Chzzk platform without modifying, executing operations, or deleting data. It is a straightforward search/lookup operation with no side effects, fitting the Read category. The low severity reflects minimal risk from misuse—an AI agent searching channels cannot harm users or data.
From the tool's definition Tool name is 'search_channels' and description states 'Search Chzzk channels by CHANNEL NAME' with results including channel information. The verb 'search' and 'look up' indicate read-only retrieval.
Attacks that exploit this kind of access
Search Chzzk channels by CHANNEL NAME. Use this to look up a specific streamer by their handle. Each result includes an. 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_channels: 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_channels 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_channels 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_channels. 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_channels 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 →