Runway ML

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/mindstone-mcp-server-runway

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

6 read · 12 write · 5 delete

Secrets

1 (API keys, tokens or passwords)

Install scripts

Not scanned yet

Runs as

Node.js package

Tools (23)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• cancel_runway_taskcan change or delete data

  Cancel a pending/running task or delete a completed task. Saves credits if cancelled before completion.

• character_performance

  Animate a character with facial expressions and body movements from a reference performance video (Act-Two). MODEL: act_two. 5 credits/sec. Output duration matches reference video length. WORKFLOW: Returns task_id → poll or use wait_for_runway_task.

• check_runway_taskread-only

  Check the status of any Runway generation task. STATUS VALUES: PENDING → THROTTLED → RUNNING → SUCCEEDED (output URLs) or FAILED. TIP: Use wait_for_runway_task for automatic polling.

• configure_runway_api_keycan change or delete data

  Save your Runway API key. Call this when the user provides their key. WHERE TO GET A KEY: Go to https://dev.runwayml.com/ → API Keys. Add credits in Billing (min $10 = 1000 credits).

• create_custom_voicecan change or delete data

  Create a custom voice from a text description of desired voice characteristics. MODELS: eleven_multilingual_ttv_v2 (default), eleven_ttv_v3 (newer). Check status with list_custom_voices. Once READY, use its ID with generate_speech.

• delete_custom_voicecan change or delete data

  Delete a custom voice by ID. This is permanent and cannot be undone.

• download_runway_outputcan change or delete data

  Download a Runway output (video, image, audio) to a local file. Use after a task succeeds to save the output locally. output_path MUST live inside RUNWAY_DOWNLOAD_ROOT (default ~/Downloads/runway-mcp). Sensitive paths (~/.ssh, ~/.aws, /etc, ~/.bashrc, ~/.zshrc) are refused even when the root would otherwise permit them. By default, refuses to overwrite an existing file (atomic flags: "wx") — pass overwrite: true to clobber.

• dub_audio

  Translate and dub audio into a different language, cloning the original speaker's voice. COST: 1 credit per 2 seconds. WORKFLOW: Returns task_id → poll or use wait_for_runway_task.

• generate_image

  Generate an image from text, optionally with reference images for style/content guidance. MODELS: gen4_image (high quality), gen4_image_turbo (fast/cheap), gemini_2.5_flash (Google Gemini). REFERENCE IMAGES: Tag with short label (e.g., "cat"), use @tag in prompt. WORKFLOW: Returns task_id → poll with check_runway_task or use wait_for_runway_task.

• generate_sound_effect

  Generate sound effects from a text description. COST: 1 credit per 6 seconds. WORKFLOW: Returns task_id → poll or use wait_for_runway_task.

• generate_speech

  Generate spoken audio from text using ElevenLabs voices via Runway. 49 voice presets available. Can also use custom voice IDs (eleven_multilingual_v2 only). MODELS: eleven_multilingual_v2 (default), eleven_v3 (expressive; supports audio tags like [laughs] and [whispers] in the text; preset voices only). COST: 1 credit per 50 characters. WORKFLOW: Returns task_id → poll or use wait_for_runway_task.

• generate_video_from_image

  Animate a still image into a video. Supports first-frame (and optionally last-frame) keyframe control. MODELS: gen4.5 (flagship), gen4_turbo (fast/cheap), veo3.1 (best quality + audio), veo3.1_fast, veo3 (deprecated upstream). WORKFLOW: Returns task_id → poll with check_runway_task or use wait_for_runway_task.

• generate_video_from_text

  Create a video entirely from a text description. MODELS: gen4.5 (flagship), veo3.1 (best + audio), veo3.1_fast, veo3 (deprecated upstream). WORKFLOW: Returns task_id → poll or use wait_for_runway_task.

• generate_video_from_video

  Re-style or transform an existing video using Aleph 2.0. MODEL: aleph2 (only option). 28 credits/sec (56 credit minimum). Input video must be 30 seconds or shorter. WORKFLOW: Returns task_id → poll or use wait_for_runway_task.

• get_runway_balanceread-only

  Check your Runway credit balance, usage tier limits, and today's usage by model. 1 credit = $0.01.

Signals

Stars

13

Forks

4

Open issues

1

Weekly downloads

39

Last commit (this folder)

Aug 10, 2026 (2 months ago)

Last release

Aug 10, 2026 (2 months ago)

Last package publish

Aug 10, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.mindstone/mcp-server-runway

Version

0.4.1

Auth

API key

Packages

npm @mindstone/mcp-server-runway

License

License unknown

Repository

github.com/mindstone/mcp-servers

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql