What it does
The server exposes tools for text-to-video and image-to-video generation, including a Director Mode for image-to-video with more creative control. It supports the minimax-t2v, minimax-i2v and minimax-i2v-director models. Further tools check the status and result of a generation task, query several tasks at once, and list the available models and API actions.
It suits people who want to create videos from a text prompt or a reference image directly from an MCP-compatible client such as Claude, VS Code, Cursor or Codex, and then track those generation jobs from the same place.
There are three ways to connect: a hosted endpoint with browser OAuth sign-in, a hosted endpoint with an AceDataCloud API token sent in an Authorization header, or a local stdio process that is given the token through the ACEDATACLOUD_API_TOKEN variable. Every route calls the AceDataCloud API, so an AceDataCloud account and an API key for the required service are needed. The token should be kept in a secret store or environment variable.
Limitations and requirements
Requires an AceDataCloud account and an API key with access to the required service and model; the key's expiration, usage limit and account balance must cover the requests. The hosted service is metered and pricing should be reviewed before use. Dynamic Client Registration registers the client application and is not an API key. Do not configure both an OAuth login and a fixed Authorization header for the same server. Tokens must not be placed in prompts, shared workflows, screenshots or Git commits.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 15 Nov 2026 · its page on the source
io.github.AceDataCloud/mcp-hailuo
MCP server for Hailuo (MiniMax) AI video generation
v2026.11.15.0As shown on registry.modelcontextprotocol.io when we last read it