Get users who liked a TikTok video. Example: get_video_likes(
AI agents call get_video_likes to retrieve information from TikTok Complete MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches and queries TikTok engagement data (likes/likers) which is a read operation with no side effects. However, it accesses personal user information (identity of video likers) at scale, which raises privacy concerns for individuals whose engagement data is exposed without consent.
From the tool's definition Tool is named 'get_video_likes' and retrieves data about users who liked a TikTok video. The description confirms it retrieves information without modifying data.
Attacks that exploit this kind of access
Get users who liked a TikTok video. Example: get_video_likes(. It is categorised as a Read tool in the TikTok Complete MCP Server MCP Server, which means it retrieves data without modifying state.
Register the TikTok Complete MCP Server MCP server in PolicyLayer and add a rule for get_video_likes: 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 TikTok Complete MCP Server. Nothing to install.
get_video_likes 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_video_likes 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_video_likes. 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_video_likes is provided by the TikTok Complete MCP Server MCP server (josephtandle/tiktok-complete). 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 →