Runway API
Generate images and videos using the Runway API.

Video sped up for demo purposes
Runway API MCP Server
This repository holds the code for a MCP server that calls the Runway API.
Tools
The following tools are available in this MCP:
| Tool Name | Description | Parameters |
|---|---|---|
runway_generateVideo | Generates a video from an image and a text prompt | - promptImage - promptText (optional) - ratio - duration |
runway_generateImage | Generates an image from a text prompt, and reference images | - promptText - referenceImages (note that uploaded images won't work as references, only previously generated ones, or URLs to images will work.) - ratio |
runway_upscaleVideo | Upscale a video to a higher resolution | - videoUri |
runway_editVideo | Edits a video, optionally provide reference images. | - videoUri, referenceImages, promptText |
runway_getTask | Gets the details of a task | - taskId |
runway_cancelTask | Cancels or deletes a task | - taskId |
runway_getOrg | Get organization information | |
Prerequisites
Before starting, you'll need to have setup your Developer account on the Runway API, setup Billing, and also created an API Key.
You'll also need Node.js setup.
Setup
-
Clone this repository and save it to a folder on your computer. Remember where you saved this folder because you'll need it in a later step.
-
Run
npm installin the folder, thennpm run build. You should now see a new folder calledbuildwith aindex.jsfile inside.
Using the MCP with Claude Desktop
- Follow the MCP quickstart instructions to setup a config file for Claude. If you already have it, open it by running:
MacOS
open ~/Library/Application\ Support/Claude/claude_desktop_config.json
Windows
notepad %APPDATA%\Claude\claude_desktop_config.json
- Add the
runway-api-mcp-serverto the config, make sure to replace the file path and Runway API key.
{
"mcpServers": {
"runway-api-mcp-server": {
"command": "node",
"args": [
"<ABSOLUTE_PATH_TO_YOUR_CLONED_REPO_FROM_STEP_1>/build/index.js"
],
"env": {
"RUNWAYML_API_SECRET": "<YOUR_RUNWAY_API_KEY_HERE>",
"MCP_TOOL_TIMEOUT": "1000000"
}
}
}
}
- Now restart Claude Desktop, and you should see the
runway-api-mcp-serverin Claude's tools:

- Now, try asking Claude to generate images or videos!
[!NOTE]
Images generated by the Runway API lives only for 24 hours at the generated link. There is no way to recover them after this link expires. Make sure to download the images before they expire.
Похожие серверы
Scout Monitoring MCP
спонсорPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
спонсорAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
LambdaTest MCP Server
LambdaTest MCP Servers ranging from Accessibility, SmartUI, Automation, and HyperExecute allows you to connect AI assistants with your testing workflow, streamlining setup, analyzing failures, and generating fixes to speed up testing and improve efficiency.
MCP Tools
Provides file system and command execution tools for LLM clients like Claude Desktop.
Rug-Check-MCP
Detects potential risks in Solana meme tokens to help avoid rug pulls and unsafe projects.
MCP Client for Ollama
A Python client that connects local LLMs via Ollama to Model Context Protocol servers, enabling them to use tools.
Vibetest Use
Automated QA testing for websites to find UI bugs, broken links, and accessibility issues.
Markdown Navigation MCP
An MCP server that provides efficient navigation and reading of large markdown files using ctags to reduce context usage
cli-mcp
A command-line interface (CLI) client for calling tools from local and remote MCP servers.
BlenderMCP
Connects Blender to Claude AI via the Model Context Protocol (MCP), enabling direct interaction and control for prompt-assisted 3D modeling, scene creation, and manipulation.
Reports MCP Server
Manages penetration testing reports and vulnerabilities via a REST API.
nUR MCP Server
An intelligent robot control middleware for natural language interaction with industrial robots, powered by LLMs. It integrates with Universal Robots and supports real-time, multi-robot control.