Luma MCP

First, a quick disambiguation: this page is about the Luma Dream Machine video model, not the lu.ma events app that shares the name. Luma shipped its own official MCP server, so an agent can point at Luma and call Luma's own models. That is the right tool when Luma's models are exactly what you need. It is also single vendor: the server exposes one roster, and your agent is wired to it alone.

Wireflow takes the opposite shape. It is a hosted node canvas where you assemble a video workflow, then publish it. The flow behind this page is real: a text prompt feeds a GPT Image 2.5 Flare still, and that still feeds a Gemini Omni Flash clip and a compose step. Publishing turns that graph into a hosted MCP tool and a hosted video API for agents at once, so an agent can pick the best model per shot instead of one vendor's stack.

When an agent can only call one vendor's model at a time, it has to orchestrate every step itself: prompt the image model, wait, hand the result to the video model, wait again, handle each failure. That logic lives in the agent, so it breaks when the agent changes. Move the steps onto a canvas and the orchestration becomes the tool, not the agent's problem.

On Wireflow you build that graph once, then let the agent drive it through the hosted MCP and REST layer, run after run, with no new wiring. A single call can chain a still into a clip, and the same pattern lets you swap the video node between vendors without rewiring. It sits between a focused MCP server for video editing and a full multi-model pipeline: enough structure that one tool call does real multi-step work, enough openness that you can still inspect and edit the graph.

If your product depends on Luma's specific models or the tooling built around them, use Luma's own official MCP server; those models live there, and no canvas layer changes that. Wireflow does not host every model on the market, and it will never claim to. It is also not the reasoning brain: it generates and returns media, it does not write your strategy or decide your shot list for you.

Be honest about the rest too. Wireflow is a managed, hosted service, not a self-hosted server: there are no offline or local runs, and generations cost credits per run. It earns its place when the job is bigger than one fixed vendor: pick the best model per shot, chain generation into a clip, keep one endpoint while models rotate underneath, or hand the pipeline to an agent as an MCP tool. If you want a Sora-style model in the same graph as Luma Dream Machine, compare the hosted Sora video model alternative and open the flow to read the actual graph.