Query the status of a Seedance 2.0 task by task_id. Returns running / succeeded / failed / other. On success returns video_url (and last_frame_url if return_last_frame was true). Generated URLs expire within ~24h - download promptly.
AI agents call seedance_check_task to retrieve information from Seedance 2 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only retrieves status information and URLs for previously created tasks. It does not modify, delete, execute code, or commit financial transactions. The retrieval of temporary URLs (expiring in ~24h) does not constitute a side effect that changes system state. This is a standard read operation typical of task status checking APIs.
From the tool's definition Tool description states it "Query[s] the status of a Seedance 2.0 task" and "Returns running / succeeded / failed / other" with optional video_url. This is a pure status polling/retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access seedance_check_task gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Seedance 2, and nothing reaches the server without passing your rules. This is the rule we recommend for seedance_check_task:
{
"version": "1",
"default": "deny",
"tools": {
"seedance_check_task": {}
}
}seedance_check_task is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Query the status of a Seedance 2.0 task by task_id. Returns running / succeeded / failed / other. On success returns video_url (and last_frame_url if return_last_frame was true). Generated URLs expire within ~24h - download promptly. It is categorised as a Read tool in the Seedance 2 MCP Server, which means it retrieves data without modifying state.
Register the Seedance 2 MCP server in PolicyLayer and add a rule for seedance_check_task: 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 Seedance 2. Nothing to install.
seedance_check_task 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 seedance_check_task 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 seedance_check_task. 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.
seedance_check_task is provided by the Seedance 2 MCP server (leonaiuv/seedance-2-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Seedance 2, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 Seedance 2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.