AI agents invoke create_cardnews_from_file to trigger actions in Cardnews. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool reads a file from the filesystem and triggers an external pipeline (LLM + Puppeteer browser rendering) to produce HTML and PNG artifacts. It spans Read and Execute; the Puppeteer-based rendering and LLM invocation constitute external process execution, making Execute the appropriate category.
From the tool's definition 자막 파일을 읽어 단일 카드뉴스(HTML + PNG)를 생성한다 — reads a file and generates output using LLM content generation and Puppeteer for rendering
Attacks that exploit this kind of access
.vtt/.srt/.txt 자막 파일을 읽어 단일 카드뉴스(HTML + PNG)를 생성한다. It is categorised as a Execute tool in the Cardnews MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cardnews MCP server in PolicyLayer and add a rule for create_cardnews_from_file: 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_from_file is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the create_cardnews_from_file 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_from_file. 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_from_file 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 →