AI agents call search_youtube to retrieve information from Scavio 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 and retrieves publicly available YouTube video metadata. It has no side effects, does not modify data, execute code, delete content, or move money. The results are informational only. This is a straightforward Read operation with minimal security risk.
From the tool's definition Tool description states it 'Search YouTube and return video results as JSON' with metadata like video ID, title, channel, duration, view count, and upload date. No modification, deletion, or execution capabilities are mentioned.
Attacks that exploit this kind of access
Search YouTube and return video results as JSON. Each result includes video ID, title, channel, duration, view count, and upload date. Use when the user asks to find YouTube videos on a topic. It is categorised as a Read tool in the Scavio MCP Server, which means it retrieves data without modifying state.
Register the Scavio MCP server in PolicyLayer and add a rule for search_youtube: 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 Scavio. Nothing to install.
search_youtube 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_youtube 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_youtube. 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_youtube is provided by the Scavio MCP server (@scavio/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 →