时间轴拖拽控制
AI agents invoke timeline_scrubber to trigger actions in GSAP MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool controls the scrubbing/dragging of an animation timeline, which constitutes executing an interactive operation that manipulates animation playback state. It's not purely reading data nor creating/modifying stored data, but rather triggering an external operation (timeline control). The description is minimal (Chinese only), which lowers confidence slightly.
From the tool's definition '时间轴拖拽控制' translates to 'timeline scrubbing/drag control' - triggers interactive control of animation timeline playback
Attacks that exploit this kind of access
时间轴拖拽控制. It is categorised as a Execute tool in the GSAP MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the GSAP MCP Server MCP server in PolicyLayer and add a rule for timeline_scrubber: 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 GSAP MCP Server. Nothing to install.
timeline_scrubber is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the timeline_scrubber 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 timeline_scrubber. 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.
timeline_scrubber is provided by the GSAP MCP Server MCP server (lillard01/gsap-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 →