Runway ML

io.github.mindstone由 GitHub 账号 mindstone 发布v0.4.2更新于 Nov 3, 2026

Runway ML MCP 服务器:AI 视频、图像、音频、语音生成与任务管理

AI 翻译由 AI 模型根据下方的原文描述翻译,可能有误。

原文描述

Runway ML MCP server: AI video, image, audio, voice generation, and task management

已验证STDIO仅桌面媒体与设计AI 与机器学习

概览

Runway ML 的本地 MCP 服务;无需登录;STDIO。

暂无 AI 概览:以下信息来自注册中心条目和服务本身。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Runway ML,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

@mindstone/mcp-server-runway

[npm version] [License: FSL-1.1-MIT]

Runway ML MCP server for Model Context Protocol hosts. Generate AI video, images, audio, speech, sound effects, and manage custom voices — all through a standardised MCP interface powered by Runway's generative AI models.

Status

Requirements

  • Node.js 20+
  • npm

One-click install

[Add to Cursor] [Add to VS Code] [Add to VS Code Insiders]

After clicking the button, your host will prompt you to fill: RUNWAYML_API_SECRET, RUNWAY_REQUEST_TIMEOUT_MS, RUNWAY_UPLOAD_TIMEOUT_MS.

Manual config for Claude Desktop / Claude Code / Goose / Continue.dev (Runway ML)
json
{  "mcpServers": {    "Runway ML": {      "command": "npx",      "args": [        "-y",        "@mindstone/mcp-server-runway"      ],      "env": {        "RUNWAYML_API_SECRET": "",        "RUNWAY_REQUEST_TIMEOUT_MS": "60000",        "RUNWAY_UPLOAD_TIMEOUT_MS": "600000"      }    }  }}

Quick Start

Install & build

bash
cd <path-to-repo>/connectors/runwaynpm installnpm run build

npx (once published)

bash
npx -y @mindstone/mcp-server-runway

Local

bash
node dist/index.js

Configuration

Environment variables

  • RUNWAYML_API_SECRET — Runway API key (from dev.runwayml.com)
  • MCP_HOST_BRIDGE_STATE — optional path to a host bridge state file used for credential management
  • MINDSTONE_REBEL_BRIDGE_STATE — backwards-compatible alias for MCP_HOST_BRIDGE_STATE
  • RUNWAY_REQUEST_TIMEOUT_MS — optional override (positive integer ms, max 30 min) for the outbound HTTP request timeout applied to Runway JSON API and host-bridge calls. Default: 60000 (60s). Raise this if you see TIMEOUT errors on slow submits; lower it if you want tighter bounds.
  • RUNWAY_UPLOAD_TIMEOUT_MS — optional override (positive integer ms, max 30 min) for the signed-URL upload leg of uploadEphemeral (large local-file uploads). Default: 600000 (10 min). Sized for up-to-200MB uploads on typical consumer uplinks (~5 Mbps) with comfortable headroom; raise for slower connections or lower for tighter bounds.

Host configuration examples

Claude Desktop / Cursor

json
{  "mcpServers": {    "Runway": {      "command": "npx",      "args": ["-y", "@mindstone/mcp-server-runway"],      "env": {        "RUNWAYML_API_SECRET": "your-api-key"      }    }  }}

Local development (no npm publish needed)

json
{  "mcpServers": {    "Runway": {      "command": "node",      "args": ["<path-to-repo>/connectors/runway/dist/index.js"],      "env": {        "RUNWAYML_API_SECRET": "your-api-key"      }    }  }}

Tools (23)

Configuration

  • configure_runway_api_key — Save your Runway API key

Video

  • generate_video_from_image — Animate a still image into a video
  • generate_video_from_text — Create a video from a text description
  • generate_video_from_video — Re-style or transform an existing video (Aleph 2.0)
  • character_performance — Animate a character with facial expressions and body movements (Act-Two)
  • upscale_video — Upscale a video up to 4K (Magnific Video Upscaler)

Video models: generate_video_from_image takes gen4_turbo (default), gen4.5, veo3.1 or veo3.1_fast; generate_video_from_text takes gen4.5 (default), veo3.1 or veo3.1_fast. veo3 is no longer accepted by Runway and is refused before any request; use veo3.1 or veo3.1_fast instead.

Image

  • generate_image — Generate an image from text, optionally with reference images

Audio

  • generate_speech — Generate spoken audio from text using ElevenLabs voices
  • generate_sound_effect — Generate sound effects from a text description
  • swap_voice — Replace the voice in an audio or video file
  • dub_audio — Translate and dub audio into a different language
  • isolate_voice — Isolate voice from background audio

Voices

  • list_custom_voices — List all custom voices you've created
  • create_custom_voice — Create a custom voice from a text description
  • preview_voice — Generate a short audio preview of a voice
  • delete_custom_voice — Delete a custom voice

Task management

  • check_runway_task — Check the status of a generation task
  • wait_for_runway_task — Wait for a task to complete (auto-poll)
  • cancel_runway_task — Cancel or delete a task
  • download_runway_output — Download a Runway output to a local file
  • upload_media — Upload a local file to Runway's ephemeral storage

Account

  • get_runway_balance — Check credit balance, tier limits, and usage
  • query_credit_usage — Query detailed credit usage by model and day

Licence

FSL-1.1-MIT — Functional Source License, Version 1.1, with MIT future licence. The software converts to MIT licence on 2030-04-08.

来源:connectors/runway/README.md,提交 9b9aa57

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

2
  1. v0.4.2最新Nov 3, 2026
  2. v0.4.1Sep 16, 2026

评分

已满足适用检查项的 40%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。