render_video · Flash Cast MCP: Risk & Policy

WHAT IT DOES

What render_video does on Flash Cast

AI agents invoke render_video to trigger actions in Flash Cast. 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.

WHY IT NEEDS A POLICY

Why render_video needs a policy

The tool initiates a long-running external operation (2-10 minutes) combining text-to-speech, screen capture, and audio mixing. This is a classic Execute category: it runs an external process whose effects depend on prior configuration arguments. It is not merely writing data reversibly — it triggers a pipeline with real resource consumption.

From the tool's definition 触发视频渲染（TTS + 录屏 + 混音，约 2-10 分钟）— triggers a multi-step external rendering pipeline (TTS, screen recording, audio mixing) that consumes compute resources and produces output artifacts

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

render_video Rate-limited

render_video stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "render_video": {
      "limits": [
        {
          "counter": "render_video_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Flash Cast, so you can run agents against it safely.

FAQ

Questions about render_video

What does the render_video tool do? +

触发视频渲染（TTS + 录屏 + 混音，约 2-10 分钟）。必须先 get_render_preview 并由用户确认；user_confirmed_content 必须为 true。返回 progressUrl 与本机进度页。. It is categorised as a Execute tool in the Flash Cast MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on render_video? +

Register the Flash Cast MCP server in PolicyLayer and add a rule for render_video: 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 Flash Cast. Nothing to install.

What risk level is render_video? +

render_video is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit render_video? +

Yes. Add a rate_limit block to the render_video 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.

How do I block render_video completely? +

Set action: deny in the PolicyLayer policy for render_video. 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.

What MCP server provides render_video? +

render_video is provided by the Flash Cast MCP server (trtian/flash-cast-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.