This MCP server provides tools to interact with the RunwayML and Luma AI APIs for video and image generation tasks.
Connect MCP Video Gen to Claude, Cursor or any other MCP client and it stops being a tab you switch to. This MCP server provides tools to interact with the RunwayML and Luma AI APIs for video and image generation tasks. The mcp video gen mcp server is what makes that connection.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
provider — (Optional) runwayml (default) or lumaaipromptText — (Required) The text promptrunway_model — (Optional) Runway model (e.g., "gen-2")runway_resolution — (Optional) Runway resolution (1280:768 or 768:1280)runway_watermark — (Optional) Boolean, default falseluma_model — (Optional) Luma model (ray-flash-2, ray-2 (default), ray-1-6)luma_aspect_ratio — (Optional) Luma aspect ratio (e.g., 16:9 (default), 1:1)luma_loop — (Optional) Booleanduration — (Optional) Video duration in seconds (number)seed — (Optional) Generation seed (number)promptImage — (Required) URL of the input image, or for Runway, an array [{uri: "url", position: "first" | "last"}]runway_duration — (Optional) Runway duration (5 (default) or 10)Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
Configuration is passed through the environment: RUNWAYML_API_SECRET, LUMAAI_API_KEY, OPENROUTER_API_KEY, PRODUCT_IMAGE_URL, YOUR_IMAGE_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
enhance_prompt tool)This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. MCP Video Gen's toolset — provider, promptText, runway_model and 11 more — is a fair guide to whether it matches your workflow. It is maintained by wheattoast11; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against MCP Video Gen's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| provider | (Optional) runwayml (default) or lumaai. |
| promptText | (Required) The text prompt. |
| runway_model | (Optional) Runway model (e.g., "gen-2"). |
| runway_resolution | (Optional) Runway resolution (1280:768 or 768:1280). |
| runway_watermark | (Optional) Boolean, default false. |
| luma_model | (Optional) Luma model (ray-flash-2, ray-2 (default), ray-1-6). |
| luma_aspect_ratio | (Optional) Luma aspect ratio (e.g., 16:9 (default), 1:1). |
| luma_loop | (Optional) Boolean. |
| duration | (Optional) Video duration in seconds (number). |
| seed | (Optional) Generation seed (number). |
| promptImage | (Required) URL of the input image, or for Runway, an array [{uri: "url", position: "first" | "last"}]. |
| runway_duration | (Optional) Runway duration (5 (default) or 10). |
| runway_ratio | (Optional) Runway resolution (1280:768 or 768:1280). |
| original_prompt | (Required) The prompt to enhance. |
{
"mcpServers": {
"runway-luma-server": {
"command": "node",
"args": ["/full/path/to/runwayml-mcp-server/build/server-index.js"],
"env": {
"RUNWAYML_API_SECRET": "your_runwayml_api_secret_here",
"LUMAAI_API_KEY": "your_luma_api_key_here",
"OPENROUTER_API_KEY": "your_openrouter_api_key_here"
},
"disabled": false,
"autoApprove": []
}
}
}Configuration as documented by the project. Restart the client after saving.
enhance_prompt tool)| Variable | Description | Required |
|---|---|---|
| RUNWAYML_API_SECRET | Credential the server authenticates with. | Yes |
| LUMAAI_API_KEY | Credential the server authenticates with. | Yes |
| OPENROUTER_API_KEY | Credential the server authenticates with. | Yes |
| PRODUCT_IMAGE_URL | Endpoint or connection string the server talks to. | Yes |
| YOUR_IMAGE_URL | Endpoint or connection string the server talks to. | Yes |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.