Answer a question about a video's contents using state-of-the-art generative AI models.
AI agents call query_video to retrieve information from Perception-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves information from video files using generative AI models. It performs analysis and returns answers about video content without creating, modifying, deleting, or executing external operations. The operation is purely informational and read-only, making it a Read category risk with low severity.
From the tool's definition Tool description states 'Answer a question about a video's contents' — a retrieval and analysis operation with no side effects or state modifications.
Attacks that exploit this kind of access
Answer a question about a video's contents using state-of-the-art generative AI models. It is categorised as a Read tool in the Perception-MCP MCP Server, which means it retrieves data without modifying state.
Register the Perception- MCP server in PolicyLayer and add a rule for query_video: 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 Perception-MCP. Nothing to install.
query_video 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 query_video 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 query_video. 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.
query_video is provided by the Perception- MCP server (lintyourcode/perception-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 →