Restart the video from the beginning.
AI agents invoke restart_playback to trigger actions in MCP Media Server. 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 executes a command that affects the state of an external system (the media player), even though the effect is limited and reversible. It does not retrieve data (Read), create/modify files (Write), permanently delete anything (Destructive), or involve financial transactions (Financial). The blast radius is minimal—restarting a video—making severity low.
From the tool's definition Tool 'restart_playback' triggers an external operation (restarting video playback) on the system's default media player.
Attacks that exploit this kind of access
Restart the video from the beginning. It is categorised as a Execute tool in the MCP Media Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Media Server MCP server in PolicyLayer and add a rule for restart_playback: 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 MCP Media Server. Nothing to install.
restart_playback 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 restart_playback 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 restart_playback. 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.
restart_playback is provided by the MCP Media Server MCP server (neal3000/mcp_media_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 →