create_avatar_by_video
AI agents use create_avatar_by_video to create or update resources in ShiLiu MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ShiLiu MCP Server environment.
Based on the tool name and sibling tools (create_avatar_by_image, create_speaker, create_video_by_text), this tool likely creates a digital human avatar from a video input, which is a Write operation (creating new data/resource). The empty description lowers confidence. Severity is medium as it consumes platform credits and creates content, but is not destructive or financial in nature.
From the tool's definition Tool name 'create_avatar_by_video' and server context of avatar creation; description is empty and uninformative.
Attacks that exploit this kind of access
create_avatar_by_video. It is categorised as a Write tool in the ShiLiu MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ShiLiu MCP Server MCP server in PolicyLayer and add a rule for create_avatar_by_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 ShiLiu MCP Server. Nothing to install.
create_avatar_by_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 create_avatar_by_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 create_avatar_by_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.
create_avatar_by_video is provided by the ShiLiu MCP Server MCP server (shiliu-ai/shiliu-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 →