AI agents use generate_reference2video_to_video to create or update resources in Vidu MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vidu MCP environment.
Based on the naming pattern consistent with sibling tools (generate_img_to_video, generate_text_to_video, etc.) and the server description mentioning 'reference content', this tool likely generates a video from reference video input. Video generation is a Write operation (creates new content). The description is empty, so confidence is reduced. No financial, destructive, or execute semantics are apparent.
From the tool's definition Tool name 'generate_reference2video_to_video' and server context: 'Provides access to Vidu's video generation models for creating high-quality videos from text, images, and reference content'
Attacks that exploit this kind of access
generate_reference2video_to_video. It is categorised as a Write tool in the Vidu MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Vidu MCP server in PolicyLayer and add a rule for generate_reference2video_to_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 Vidu MCP. Nothing to install.
generate_reference2video_to_video is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the generate_reference2video_to_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 generate_reference2video_to_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.
generate_reference2video_to_video is provided by the Vidu MCP server (shengshu-ai/vidu-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 →