Runway Api MCP Server

This repository holds the code for a MCP server that calls the Runway API.

Remote serverstreamable-httpGo

What is the Runway Api MCP server?

Runway Api MCP server exists for a simple reason — assistants are far more useful when they can act on Runway Api directly instead of describing what you should do. This repository holds the code for a MCP server that calls the Runway API.

What the assistant can call

Once Runway Api is connected, these are the calls the assistant has available:

  • ratio — duration
  • runway_listModels — Lists available models per capability and the recommended default for each
  • runway_generateVideo — Generates a video from an image and a text prompt
  • runway_generateImage — Generates an image from a text prompt, and reference images
  • runway_upscaleVideo — Upscale a video to a higher resolution
  • runway_editVideo — Edits a video, optionally provide reference images
  • runway_generateAudio — Generates spoken audio (text-to-speech) from text
  • runway_getTask — Gets the details of a task
  • runway_cancelTask — Cancels or deletes a task
  • runway_getOrg — Get organization information

Configuration and credentials

You will need 2 environment variables: RUNWAYML_API_SECRET, MCP_TOOL_TIMEOUT. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

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.

Setting it up

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Choosing this one

Plenty of planning and project tracking servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Runway Api's toolset — ratio, runway_listModels, runway_generateVideo and 7 more — is a fair guide to whether it matches your workflow. It is maintained by runwayml; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 10 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Runway Api.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the runway api mcp server does with a few real requests.

Available tools

ToolWhat it does
ratioduration
runway_listModelsLists available models per capability and the recommended default for each
runway_generateVideoGenerates a video from an image and a text prompt
runway_generateImageGenerates an image from a text prompt, and reference images
runway_upscaleVideoUpscale a video to a higher resolution
runway_editVideoEdits a video, optionally provide reference images.
runway_generateAudioGenerates spoken audio (text-to-speech) from text
runway_getTaskGets the details of a task
runway_cancelTaskCancels or deletes a task
runway_getOrgGet organization information

How to install the Runway Api MCP server

{
  "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"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

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.

VariableDescriptionRequired
RUNWAYML_API_SECRETCredential the server authenticates with.Yes
MCP_TOOL_TIMEOUTConfiguration value read at startup.Optional

Example prompts to try

  • Use Runway Api to ratio.
  • Use Runway Api to runway listModels.
  • Use Runway Api to runway generateVideo.

Frequently asked questions

It connects Runway Api to MCP-compatible AI assistants such as Claude and Cursor, exposing 10 tools (ratio, runway_listModels, runway_generateVideo, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Runway Api directly.