Get captions for a video in specified language
AI agents call get_captions 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 captions (text data) from a video. It has no side effects, does not modify data, does not execute code, and does not delete anything. It is a straightforward read/fetch operation on publicly available video metadata. The low severity reflects minimal risk if misused by an AI agent, as it only accesses already-public caption data.
From the tool's definition Tool name is 'get_captions' and description states 'Get captions for a video in specified language' — this is a retrieval operation that extracts existing metadata without modifying or executing anything.
Attacks that exploit this kind of access
Get captions for a video in specified language. 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_captions: 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_captions 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_captions 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_captions. 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_captions is provided by the YouTube MCP Server MCP server (nattyraz/youtube-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 →