play_video · Social Video MCP: Risk & Policy

WHAT IT DOES

What play_video does on Social Video

AI agents invoke play_video to trigger actions in Social Video. 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 play_video needs a policy

This tool executes an external operation (launching and controlling an mpv player instance) whose effects depend directly on the arguments supplied (which video, when to start, audio mode). Although playback is non-destructive and reversible, it represents an Execute category action because it runs code/commands that control external applications.

From the tool's definition The tool 'plays a video' in 'a lightweight mpv player window' with control over 'timestamp' and 'audio_only' playback settings.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

play_video Rate-limited

play_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": {
    "play_video": {
      "limits": [
        {
          "counter": "play_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 Social Video, so you can run agents against it safely.

FAQ

Questions about play_video

What does the play_video tool do? +

Play a video from YouTube or TikTok in a lightweight mpv player window. Optionally start at a specific timestamp. Set audio_only to true for audio-only playback (great for podcasts/music while coding). It is categorised as a Execute tool in the Social Video MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on play_video? +

Register the Social Video MCP server in PolicyLayer and add a rule for play_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 Social Video. Nothing to install.

What risk level is play_video? +

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

Can I rate-limit play_video? +

Yes. Add a rate_limit block to the play_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 play_video completely? +

Set action: deny in the PolicyLayer policy for play_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 play_video? +

play_video is provided by the Social Video MCP server (ronantakizawa/social-video-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.