AI agents call player to retrieve information from MultiViewer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool fetches information about a specific video player by ID. This is a read/get operation with no modifications, deletions, or external triggers.
From the tool's definition "Returns the MultiViewer video player with specific id" — retrieves/queries data about a player instance with no side effects.
Documented attack patterns abuse exactly the kind of access player gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MultiViewer, and nothing reaches the server without passing your rules. This is the rule we recommend for player:
{
"version": "1",
"default": "deny",
"tools": {
"player": {}
}
}player is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Returns the MultiViewer video player with specific id. It is categorised as a Read tool in the MultiViewer MCP Server, which means it retrieves data without modifying state.
Register the MultiViewer MCP server in PolicyLayer and add a rule for player: 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 MultiViewer. Nothing to install.
player is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the player 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 player. 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.
player is provided by the MultiViewer MCP server (robspectre/mvf1). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MultiViewer, 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.
21 MultiViewer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.