How do I use Runway ML with my AI client?

You connect this MCP by providing your Runway API key in the Vinkius configuration. Once connected, you can simply type instructions to your AI client to trigger video generations.

Can I stop a video from generating if I don't like it?

Yes. You can use the cancel_task capability to stop a running generation immediately to save your credits.

What models are available through this MCP?

You have access to Gen-3 Alpha Turbo, Gen-4 Turbo, and standard text-to-video models.

How do I check if my video is ready?

You can ask your AI client to list your recent tasks or check the status of a specific task ID to see if it has succeeded.

Can I turn a still photo into a video?

Yes. You can use the image_to_video or image_text_to_video capabilities to animate images using text prompts or direct motion guidance.

How can I preview the output without fully committing my prompt?

Video generation actions using the Runway engines are directly invoked through asynchronous background tasks. Instead of an exact real-time preview, you can start small 5-second generations or iterate closely on your prompt texts until they produce the final aesthetic you want.

Does this integration process video rendering in real-time?

No. Video rendering is asynchronous. When you submit a prompt or an image, the AI will dispatch a background task to Runway's servers and receive a 'task_id'. You will need to ask the AI to verify the status of this task later, usually after a few minutes, to fetch the final video URL.

Can I use Gen-4 models for free?

No. Runway requires credits for all generations, and Gen-4 Turbo consumes significantly more credits than earlier models or standard actions. You must maintain sufficient active credits or a paid subscription on your Runway account for the AI to successfully execute the rendering jobs.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Runway ML to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn text and images into cinematic video clips through chat.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Runway ML API.

01
Cancel task
Stops a running video generation immediately. This action cannot be undone.
02
Gen3 turbo
Generates quick 5-second video clips using the Gen-3 Alpha Turbo model.
03
Gen4 turbo
Produces high-quality video clips using the Gen-4 Turbo model.
04
Get organization
Checks your Runway ML organization details and current credit balance.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Runway ML API.

05
Get task
Retrieves the current status and the final output URL for a specific generation task.
06
Image text to video
Creates a video by combining a source image with a text-based director prompt.
07
Image to video
Animates a single still image into a video clip based on your chosen model and duration.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Runway ML API.

08
Interpolate
Blends two different keyframe images to create a smooth motion transition between them.
09
Text to video
Synthesizes a new video clip from a text prompt using specified models and durations.
10
List tasks
Shows a list of your most recent video generation tasks.

Real work

What teams actually run

Rapid Storyboarding

A director describes a scene to generate a visual reference for a film shoot.

B-Roll Generation

A creator generates specific background footage to fill gaps in a video edit.

Image Animation

A designer turns a static product photo into a moving promotional clip.

Visual Transitions

An editor creates smooth motion between two different visual concepts using interpolation.

Automate a task

Put Runway ML API to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Runway ML API works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Runway ML API to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

944ms average. Fast in production.

Runway ML API is checked daily against the live service.

Daily averagePeak 1362ms

Oct 3Today

Fastest day: 793ms
Slowest day: 1362ms
14-day trend: Slowing+47%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Runway ML API, so you can see the experience inside your AI.

It does not authenticate your account with Runway ML API. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Runway ML API Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_fxPMozx8tTYwy0f2CIAyhsmnGRvf4U3doJGXFGQX/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Runway ML API capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "runway-ml-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_fxPMozx8tTYwy0f2CIAyhsmnGRvf4U3doJGXFGQX/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Runway ML API in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Runway ML API owners hand off.

Creative professionals and content creators who need to prototype video quickly.

01
Creative Directors
They prompt the AI to build storyboards and conceptual scene prototypes.
02
Media Teams
They use the MCP to generate commercial grade sequences from text.
03
Social Content Creators
They generate B-roll footage directly from prompt instructions.

FAQ

Questions Runway ML API owners ask.

01
How do I use Runway ML with my AI client?
You connect this MCP by providing your Runway API key in the Vinkius configuration. Once connected, you can simply type instructions to your AI client to trigger video generations.
02
Can I stop a video from generating if I don't like it?
Yes. You can use the cancel_task capability to stop a running generation immediately to save your credits.
03
What models are available through this MCP?
You have access to Gen-3 Alpha Turbo, Gen-4 Turbo, and standard text-to-video models.
04
How do I check if my video is ready?
You can ask your AI client to list your recent tasks or check the status of a specific task ID to see if it has succeeded.
05
Can I turn a still photo into a video?
Yes. You can use the image_to_video or image_text_to_video capabilities to animate images using text prompts or direct motion guidance.
06
How can I preview the output without fully committing my prompt?
Video generation actions using the Runway engines are directly invoked through asynchronous background tasks. Instead of an exact real-time preview, you can start small 5-second generations or iterate closely on your prompt texts until they produce the final aesthetic you want.
07
Does this integration process video rendering in real-time?
No. Video rendering is asynchronous. When you submit a prompt or an image, the AI will dispatch a background task to Runway's servers and receive a 'task_id'. You will need to ask the AI to verify the status of this task later, usually after a few minutes, to fetch the final video URL.
08
Can I use Gen-4 models for free?
No. Runway requires credits for all generations, and Gen-4 Turbo consumes significantly more credits than earlier models or standard actions. You must maintain sufficient active credits or a paid subscription on your Runway account for the AI to successfully execute the rendering jobs.

Explore

More in AI Frontier

Connect Runway ML API to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Cancel task

Gen3 turbo

Gen4 turbo

Get organization

05-07

Get task

Image text to video

Image to video

08-10

Interpolate

Text to video

List tasks

What teams actually run

Rapid Storyboarding

B-Roll Generation

Image Animation

Visual Transitions

Building your own app? The connector is yours to use.

Runway ML API Connector

Claude Desktop

Creative Directors

Media Teams

Social Content Creators

How do I use Runway ML with my AI client?

Can I stop a video from generating if I don't like it?

What models are available through this MCP?

How do I check if my video is ready?

Can I turn a still photo into a video?

How can I preview the output without fully committing my prompt?

Does this integration process video rendering in real-time?

Can I use Gen-4 models for free?

Luma AI (Generative Video & Creative) AI Connector

Kling AI (Generative Video & Image) AI Connector

Runway ML AI Connector

Leonardo.ai (Generative AI & Models) AI Connector

Suggestions

Elai AI Video AI Connector

Modelbit (ML Model Deployments) AI Connector

Pika AI Connector

Brightcove AI Connector