Search YouTube videos by query.
AI agents call youtube_search to retrieve information from Youtube Research without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries YouTube's public search index and returns matching video metadata. It has no side effects, does not modify or delete any data, and does not execute code or trigger external operations beyond standard API retrieval. The query parameter may be user-influenced but the operation itself is a simple search that returns public information. This is a classic Read category tool.
From the tool's definition Tool description states it 'Search[es] YouTube videos by query' — a retrieval operation with no modification of data. Sibling tools like youtube_video_info, youtube_transcript, youtube_trending, and youtube_playlist are all read-only metadata/content queries.
Attacks that exploit this kind of access
Search YouTube videos by query. It is categorised as a Read tool in the Youtube Research MCP Server, which means it retrieves data without modifying state.
Register the Youtube Research MCP server in PolicyLayer and add a rule for youtube_search: 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 Research. Nothing to install.
youtube_search 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 youtube_search 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 youtube_search. 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.
youtube_search is provided by the Youtube Research MCP server (plaguedoctor39/youtube-research). 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 →