AI agents call get_clips to retrieve information from Twitch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though get_clips only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
クリップの情報を取得します. It is categorised as a Read tool in the Twitch MCP Server, which means it retrieves data without modifying state.
Register the Twitch MCP server in PolicyLayer and add a rule for get_clips: 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 Twitch. Nothing to install.
get_clips 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_clips 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_clips. 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_clips is provided by the Twitch MCP server (@mtane0412/twitch-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.