AI agents call get_video_metrics to retrieve information from Mux without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves analytics and performance data from Mux Data without creating, modifying, deleting, or executing operations. It is a read-only query operation with minimal blast radius—misuse would only expose viewing patterns and performance statistics, not enable unauthorized actions or data modification.
From the tool's definition Tool description states it 'Pull[s]' metrics (video_views, player_error_rate, rebuffer_percentage, playback_score) with optional filtering. Keywords 'pull' and 'metrics' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Pull engagement and quality metrics from Mux Data: video_views, player_error_rate, rebuffer_percentage, playback_score. Optionally filtered by a specific video. It is categorised as a Read tool in the Mux MCP Server, which means it retrieves data without modifying state.
Register the Mux MCP server in PolicyLayer and add a rule for get_video_metrics: 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 Mux. Nothing to install.
get_video_metrics 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 get_video_metrics 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 get_video_metrics. 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.
get_video_metrics is provided by the Mux MCP server (nobanks/mux-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 →