Show the video using the the video path and the subtitle language code. If the subtitle language code is an empty string, the video will play with no subtitle.
AI agents invoke show_video to trigger actions in Vlc. 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 launches/controls an external application (VLC) to play a video file at a given path. It executes an external operation whose effects depend on the arguments (video path, subtitle language). It is not merely reading data, and while it can be reversed (stopped), the act of playing involves executing an external process and potentially exposing file system paths.
From the tool's definition 'Show the video using the the video path and the subtitle language code' — triggers external playback operation in VLC media player
Documented attack patterns abuse exactly the kind of access show_video gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Vlc, and nothing reaches the server without passing your rules. This is the rule we recommend for show_video:
{
"version": "1",
"default": "deny",
"tools": {
"show_video": {
"limits": [
{
"counter": "show_video_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}show_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.
Free to start. No card required.
Show the video using the the video path and the subtitle language code. If the subtitle language code is an empty string, the video will play with no subtitle. It is categorised as a Execute tool in the Vlc MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Vlc MCP server in PolicyLayer and add a rule for show_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 Vlc. Nothing to install.
show_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 show_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 show_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.
show_video is provided by the Vlc MCP server (piebro/vlc-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Vlc, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Vlc tools catalogued and risk-classified — across an index of 43,000+ MCP servers.