AI agents use create_cardnews_batch to create or update resources in Cardnews — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cardnews environment.
This tool writes/creates new data artifacts (infographic card files) in a batch process. While it involves LLM content generation and Puppeteer rendering, the core operation is file creation and writing rather than arbitrary code execution. The batch nature and file output format confirm Write category.
From the tool's definition Tool creates infographic cards (HTML+PNG output files) in batch from subtitle files. Description indicates generation of card files per episode and optional combine operation. No deletion, no code execution beyond rendering, no financial operations.
Attacks that exploit this kind of access
여러 자막 파일을 회차별 카드 1장씩 + (combine 시) 전체 병합. It is categorised as a Write tool in the Cardnews MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cardnews MCP server in PolicyLayer and add a rule for create_cardnews_batch: 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 Cardnews. Nothing to install.
create_cardnews_batch is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_cardnews_batch 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 create_cardnews_batch. 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.
create_cardnews_batch is provided by the Cardnews MCP server (leedonwoo2827-ship-it/cardnews-mcp-server). 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 →