get_video_preview
AI agents call get_video_preview to retrieve information from Youtube Context without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves preview information about a video without modifying, deleting, or executing operations. The empty description and naming pattern align with the server's stated purpose of providing context (Read category). Confidence is moderately high but not critical due to missing tool description; if 'preview' conceals any write or execute capability, classification could change.
From the tool's definition Tool name 'get_video_preview' and sibling tools (get_transcript, get_video_metadata, get_most_replayed, get_video_frame) all indicate data retrieval operations.
Attacks that exploit this kind of access
get_video_preview. It is categorised as a Read tool in the Youtube Context MCP Server, which means it retrieves data without modifying state.
Register the Youtube Context MCP server in PolicyLayer and add a rule for get_video_preview: 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 Youtube Context. Nothing to install.
get_video_preview 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_preview 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_preview. 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_preview is provided by the Youtube Context MCP server (realiti4/youtube-context-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 →