AI agents call search_videos_tool to retrieve information from YtMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search query against YouTube's public video database and returns results. It has no side effects, does not modify data, does not execute arbitrary code, and does not move money. It is a straightforward retrieval operation characteristic of Read category tools. The read-only nature of the entire server and the absence of any mutation or execution capability support low severity classification.
From the tool's definition Tool name 'search_videos_tool' and description 'Search YouTube for videos by keyword' indicate a query operation that retrieves public video metadata without modifying, deleting, or executing any actions.
Attacks that exploit this kind of access
Search YouTube for videos by keyword. It is categorised as a Read tool in the YtMCP MCP Server, which means it retrieves data without modifying state.
Register the Yt MCP server in PolicyLayer and add a rule for search_videos_tool: 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 YtMCP. Nothing to install.
search_videos_tool 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 search_videos_tool 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 search_videos_tool. 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.
search_videos_tool is provided by the Yt MCP server (utkarshchaudhary009/ytmcp). 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 →