Seek to an absolute position in the currently playing video.
AI agents invoke seek_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.
This tool controls playback of a running media player (mpv), seeking to a specific position. It triggers an external operation on a running process. No data is created, modified, or destroyed — but it executes a player control action, making Execute the appropriate category. Blast radius is low as it only affects the local video playback state.
From the tool's definition Seek to an absolute position in the currently playing video
Attacks that exploit this kind of access
Seek to an absolute position in the currently playing video. 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.
Register the Social Video MCP server in PolicyLayer and add a rule for seek_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.
seek_video 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 seek_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.
Set action: deny in the PolicyLayer policy for seek_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.
seek_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.
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 →