AI agents call download_video to retrieve information from Sora2 MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves previously generated video artifacts (MP4, WebP, JPEG files) as a read-only operation. It has no side effects on the video itself, the server state, or external systems. The operation is purely informational/retrieval-based, fitting the 'Read' category.
From the tool's definition Tool name 'download_video' and description 'Download the completed video file' indicate retrieval of existing data with no modification, deletion, or execution of operations.
Attacks that exploit this kind of access
Download the completed video file (MP4), thumbnail (WebP), or spritesheet (JPEG). Only works when status is. It is categorised as a Read tool in the Sora2 MCP MCP Server, which means it retrieves data without modifying state.
Register the Sora2 MCP server in PolicyLayer and add a rule for download_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 Sora2 MCP. Nothing to install.
download_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 download_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 download_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.
download_video is provided by the Sora2 MCP server (nanameru/sora2-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 →