Mcp Luma is a Model Context Protocol (MCP) server: MCP server for Luma Dream Machine AI video generation. In practice that means any MCP-compatible AI assistant can call Mcp Luma's tools directly — the model decides when to use them in a conversation or agent run.
You can run Mcp Luma two ways: connect to the hosted endpoint at https://luma.mcp.acedata.cloud/mcp with no local install, or run it on your own machine via the Python package mcp-luma (via uvx). Configuration happens through environment variables — you'll need ACEDATACLOUD_API_TOKEN. The current release is v2026.8.28.0, published under the MIT license, with source at AceDataCloud/LumaMCP on GitHub.
Mcp Luma is listed under Development on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Mcp Luma for AceDataCloud, claim this listing to verify ownership, earn the Verified badge, and keep the details current.