ShortlistFirst-party MCP

Runway API MCP Server

by ecosystem:runway-api

Updated September 21, 2026

AI & ReasoningMedia & MarketingSports & EntertainmentAccess · Hosted

MCP100 verdict

Connect AI clients to supported Runway media-generation and API workflows for creating or managing generative media tasks.

MCP100 Assessment

Editorial verdict

Promising creative tooling, but it remains on the Shortlist until media-generation cost, uploaded-content handling, credential scope, job side effects, and policy boundaries receive fuller independent review.

Reviewed July 30, 2026

Task Fit

Mapped

Specialized workflows

Trust

Status warning

mcp_relevance; documentation; client_coverage; tool_contract; install_supply_chain; advisory_freshness; resource_type_requirements

Maintenance

Activity observed

A dated repository or package update is available; editorial maintenance review is still pending.

Popularity

Signals available

Visible usage signals are shown for discovery only, not as proof of safety.

Best for

AI image and video generation workflows.

Not ideal for

Production use before the documented maturity gaps are resolved

Avoid if

The connected identity is broader than the task requires
Tool calls cannot be reviewed before consequential mutations

Trade-offs

The repository has a short history, no strong release track record, and requires source-based setup.

Evidence scope

Evidence

Current source snapshot

Popularity

22 MCP repository stars

81 package downloads / 30 days

Repository identity: runwayml/runway-api-mcp-server

Package identity: runway-api-mcp-server

Official npm package runway-api-mcp-server: 81 downloads / 30 days.

Stars observed August 14, 2026 · Downloads observed September 8, 2026

Exact implementation repository metric.

Exact package is documented; download evidence is unavailable.

Maintenance

Publisher activity observed August 10, 2026

Current source snapshot

Trust review

Source relationship: First-party MCP

Reviewed July 30, 2026

Sources

GitHub repository ↗

Evidence-backed setup

Install & Agents

Choose your MCP client. A client connects to the MCP server; the language model is selected inside that client. Only stored, source-backed configurations are shown.

Claude Code

Streamable HTTP

MCP100 logic checked

claude mcp add --transport http runway "https://mcp.runwayml.com/mcp"

The publisher connection details were combined with this client's official MCP transport configuration; installation was not executed by MCP100.

Verify safely: Reconnect Claude Code, complete the publisher OAuth or authentication flow if prompted, confirm runway tools are listed, and perform one read-only test.

Uninstall and revoke

Remove runway from Claude Code, clear its stored MCP OAuth credentials, and revoke the publisher authorization if it is no longer needed.

Evidence & methodology

Publisher-documented setup is not the same as MCP100 execution testing. “MCP100 logic checked” means the stored configuration shape was reviewed, not that third-party MCP software was run.

Evidence checked 2026-08-12

Evidence 1 ↗Evidence 2 ↗

Read additional publisher installation details

From the publisher README

Publisher installation details

Original client setup and configuration retained from the publisher documentation.

View original README ↗

Publisher-documented clients

Claude Desktop

These names appear in the publisher's installation documentation. MCP100-verified configurations are shown separately above when available.

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 install in the folder, then npm run build. You should now see a new folder called build with a index.js file inside. If you later modify any source files, run npm run build again to pick up the changes.

Using the MCP as a Claude Desktop extension (recommended)

This installs the server as an unpacked Claude Desktop extension, so you don't have to edit any config files by hand.

Launch Claude Desktop and open Settings.
Go to Extensions, then Advanced Settings.
Click Install Unpacked Extension and select the folder you cloned in step 1 (for example /Users/edwin/runway-api-mcp-server). Click Install on the prompt.
Get your API key from https://dev.runwayml.com, paste it into the installed extension's settings, then Enable the extension.
Now, try asking Claude to generate an image!

Using the MCP with Claude Desktop (config file)

Alternatively, register the server manually through Claude's config file.

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-server to 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-server in 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.

Loading optional publisher installation details…

Read publisher documentation

Publisher documentation

Publisher README

Original product, capability, tool, and usage documentation from the MCP publisher. Installation sections appear under Install & Agents.

View original README ↗

[!WARNING]
This repository has been archived.

If you're a developer looking to integrate with the Runway API, see: https://dev.runwayml.com/agents

For other use cases, see: https://runway.com/mcp

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_listModels`	Lists available models per capability and the recommended default for each	(none)
`runway_generateVideo`	Generates a video from an image and a text prompt	- promptImage - promptText (optional) - ratio - duration - model (optional)
`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 - model (optional)
`runway_upscaleVideo`	Upscale a video to a higher resolution	- videoUri - model (optional)
`runway_editVideo`	Edits a video, optionally provide reference images.	- videoUri, referenceImages, promptText - model (optional)
`runway_generateAudio`	Generates spoken audio (text-to-speech) from text	- promptText - voice (optional) - model (optional)
`runway_getTask`	Gets the details of a task	- taskId
`runway_cancelTask`	Cancels or deletes a task	- taskId
`runway_getOrg`	Get organization information

Generation tools accept an optional model parameter to override the recommended default. Recommended models: Nano Banana Pro (gemini_image3_pro) for images, Seedance (seedance2) for video, and Aleph (aleph2) for video editing. Valid ratio, duration, and other parameter values are model-specific, so runway_listModels returns the exact valid values and required parameters for every model — call it before choosing a ratio/duration.

Before any generation request is sent to the Runway API, the server validates the payload against OpenAPI-derived per-model constraints (allowed enums, numeric ranges, string lengths, required fields). Invalid payloads fail locally with a readable error and never hit the network.

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.

Deploy as a remote MCP server

The same code can run as an HTTP MCP server, which lets clients like claude.ai web, Cursor, Zed, and Windsurf connect to a single hosted URL instead of installing the extension locally.

Local HTTP development

RUNWAYML_API_SECRET=key_xxx npm run start:http
# server listens on http://0.0.0.0:3000/mcp
curl http://127.0.0.1:3000/healthz   # → {"ok":true}

To test from web clients (claude.ai) without deploying, use a tunnel that returns HTTPS. Cloudflared works; ngrok is currently blocked by Anthropic's connector backend:

cloudflared tunnel --url http://127.0.0.1:3000

Use the printed https://<random>.trycloudflare.com/mcp as the connector URL.

Deploying to Railway

Railway deploys the HTTP server with zero config.

npm i -g @railway/cli           # one-time
railway login
railway init                    # create a new project, link this folder
railway up                      # builds & deploys
railway domain                  # provisions https://<your-app>.up.railway.app

Set environment variables in the Railway dashboard (or railway variables):

Variable	Required	Purpose
`RUNWAYML_API_SECRET`	optional	Server-side API key. Used as fallback when `REQUIRE_AUTH=false`. Do not set for public deployments.
`REQUIRE_AUTH`	yes	Set to `true` for any public/multi-tenant deployment. Forces clients to send their key as `Authorization: Bearer <key>`.
`PORT`	auto	Injected by Railway. The server reads `process.env.PORT`.

Connect from claude.ai web:

Settings → Connectors → Add custom connector
URL: https://<your-app>.up.railway.app/mcp
Leave OAuth fields blank (Bearer-key flow)

Public deployment auth model

For public, multi-tenant hosting, every user supplies their own Runway API key:

curl -X POST https://<your-app>.up.railway.app/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "Authorization: Bearer <user_runway_key>" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

When REQUIRE_AUTH=true, requests without a Bearer header receive a 401. Bearer keys take priority over RUNWAYML_API_SECRET even when both are set.

Loading optional publisher documentation…

FAQ

What can Runway API MCP Server do?

Generate authorized image and video assets through the Runway API.

Can Runway MCP generate image, video, or audio assets?

Yes. The current source registers tools for video generation, image generation, audio generation, video editing and upscaling, plus model discovery and task management. The current source is newer than some README and manifest tool lists, so the source registration should be treated as authoritative for this snapshot.

Does Runway MCP work with Claude Code?

Yes. MCP100 reviewed an evidence-backed setup for Claude Code, but has not independently verified it with a live runtime test.

Does Runway MCP require an API key?

The official server uses a Runway API key.

Is this an official MCP?

ecosystem:runway-api is listed as First-party MCP in MCP100’s current evidence.

Current official resources:

Publisher documentation ↗

[!WARNING]
This repository has been archived.

If you're a developer looking to integrate with the Runway API, see: https://dev.runwayml.com/agents

For other use cases, see: https://runway.com/mcp

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_listModels`	Lists available models per capability and the recommended default for each	(none)
`runway_generateVideo`	Generates a video from an image and a text prompt	- promptImage - promptText (optional) - ratio - duration - model (optional)
`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 - model (optional)
`runway_upscaleVideo`	Upscale a video to a higher resolution	- videoUri - model (optional)
`runway_editVideo`	Edits a video, optionally provide reference images.	- videoUri, referenceImages, promptText - model (optional)
`runway_generateAudio`	Generates spoken audio (text-to-speech) from text	- promptText - voice (optional) - model (optional)
`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.

Deploy as a remote MCP server

The same code can run as an HTTP MCP server, which lets clients like claude.ai web, Cursor, Zed, and Windsurf connect to a single hosted URL instead of installing the extension locally.

Local HTTP development

RUNWAYML_API_SECRET=key_xxx npm run start:http
# server listens on http://0.0.0.0:3000/mcp
curl http://127.0.0.1:3000/healthz   # → {"ok":true}

To test from web clients (claude.ai) without deploying, use a tunnel that returns HTTPS. Cloudflared works; ngrok is currently blocked by Anthropic's connector backend:

cloudflared tunnel --url http://127.0.0.1:3000

Use the printed https://<random>.trycloudflare.com/mcp as the connector URL.

Deploying to Railway

Railway deploys the HTTP server with zero config.

npm i -g @railway/cli           # one-time
railway login
railway init                    # create a new project, link this folder
railway up                      # builds & deploys
railway domain                  # provisions https://<your-app>.up.railway.app

Set environment variables in the Railway dashboard (or railway variables):

Variable	Required	Purpose
`RUNWAYML_API_SECRET`	optional	Server-side API key. Used as fallback when `REQUIRE_AUTH=false`. Do not set for public deployments.
`REQUIRE_AUTH`	yes	Set to `true` for any public/multi-tenant deployment. Forces clients to send their key as `Authorization: Bearer <key>`.
`PORT`	auto	Injected by Railway. The server reads `process.env.PORT`.

Connect from claude.ai web:

Settings → Connectors → Add custom connector
URL: https://<your-app>.up.railway.app/mcp
Leave OAuth fields blank (Bearer-key flow)

Public deployment auth model

For public, multi-tenant hosting, every user supplies their own Runway API key:

curl -X POST https://<your-app>.up.railway.app/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "Authorization: Bearer <user_runway_key>" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

When REQUIRE_AUTH=true, requests without a Bearer header receive a 401. Bearer keys take priority over RUNWAYML_API_SECRET even when both are set.

Promising creative tooling, but it remains on the Shortlist until media-generation cost, uploaded-content handling, credential scope, job side effects, and policy boundaries receive fuller independent review.

Best for

Not ideal for

Avoid if

Trade-offs

Evidence

Popularity

Maintenance

Trust review

Sources

Install & Agents

Claude Code

Publisher installation details

Setup

Using the MCP as a Claude Desktop extension (recommended)

Using the MCP with Claude Desktop (config file)

What it does

Representative uses

Important limits

Context Footprint

Access & risk

Other options

Chrome DevTools MCP

Sequential Thinking MCP

JADX-AI-MCP (Part of Zin MCP Suite)

Publisher README

Runway API MCP Server

Tools

Prerequisites

Deploy as a remote MCP server

Local HTTP development

Deploying to Railway

Public deployment auth model

FAQ

Publisher installation details

Setup

Using the MCP as a Claude Desktop extension (recommended)

Using the MCP with Claude Desktop (config file)

Publisher README

Runway API MCP Server

Tools

Prerequisites

Deploy as a remote MCP server

Local HTTP development

Deploying to Railway

Public deployment auth model