Get videos for a search query.
AI agents call get_videos to retrieve information from YouTube MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about videos matching a search query without creating, modifying, deleting, or executing any operations. It has no irreversible effects and does not move money or trigger external code execution. The blast radius of misuse is minimal—worst case, an agent performs unwanted searches or gathers unwanted information about videos, but no data is altered, deleted, or financial harm occurs.
From the tool's definition Tool name 'get_videos' and description 'Get videos for a search query' indicate data retrieval with no modification or side effects. This is a search/query operation that retrieves existing YouTube content.
Attacks that exploit this kind of access
Get videos for a search query. It is categorised as a Read tool in the YouTube MCP Server MCP Server, which means it retrieves data without modifying state.
Register the YouTube MCP Server MCP server in PolicyLayer and add a rule for get_videos: 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 MCP Server. Nothing to install.
get_videos 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_videos 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_videos. 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_videos is provided by the YouTube MCP Server MCP server (temiedani/youtube-mcp-server). 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 →