Runway ML MCP server

Read from the package source without running it. The installed server may list more.

• cancel_runway_taskwrite action

  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).

• check_runway_task

  Check the status of any Runway generation task.

• configure_runway_api_key

  Save your Runway API key. Call this when the user provides their key.

• create_custom_voicewrite action

  Create a custom voice from a text description of desired voice characteristics.

• delete_custom_voicewrite action

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

• download_runway_output

  Download a Runway output (video, image, audio) to a local file.

• dub_audio

  Translate and dub audio into a different language, cloning the original speaker's voice.

• generate_image

  Generate an image from text, optionally with reference images for style/content guidance.

• generate_sound_effect

  Generate sound effects from a text description.

• generate_speech

  Generate spoken audio from text using ElevenLabs voices via Runway.

• generate_video_from_image

  Animate a still image into a video. Supports first-frame (and optionally last-frame) keyframe control.

• generate_video_from_textwrite action

  Create a video entirely from a text description.

• generate_video_from_video

  Re-style or transform an existing video using Aleph 2.0.

• get_runway_balance

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

• isolate_voice

  Isolate voice from background audio. Extracts clean speech. Input must be 4.6s-3600s.

• list_custom_voices

  List all custom voices you've created. Returns voice IDs, names, descriptions, and status.

• preview_voice

  Generate a short audio preview of a voice from a text description, without creating it.

• query_credit_usage

  Query detailed credit usage broken down by model and day. Supports date ranges up to 90 days.

• swap_voice

  Replace the voice in an audio or video file with a different voice, preserving speech content.

• upload_mediawrite action

  Upload a local file to Runway's ephemeral storage, returning a runway:// URI.

• upscale_video

  Upscale a video to a higher resolution with the Magnific Video Upscaler.

• wait_for_runway_taskwrite action

  Submit a task ID and wait for it to complete. Polls automatically.

• Code scan35 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitystatic API keys via environment variables6/15
• Maintenancelast push 0 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10

Safety score

85/100

higher than 68% of 1,293 Productivity servers

Tools

23

the typical Productivity server has 7

Tools that change things

26%

typical: 0%. Fewer write tools means less an agent can break

GitHub stars

14

more than 80% of 858 Productivity servers

Runway ML: common questions

Is Runway ML MCP server safe?

Yes, by our scan: it is graded A (85/100). Read the Runway ML safety report

How do I install Runway ML?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Runway ML need an API key?

Yes. The registry entry asks for RUNWAYML_API_SECRET.

Is Runway ML maintained?

The last commit was 11 days ago (2026-11-04). The latest release is v0.4.2.

What can I use instead of Runway ML?

Servers from other publishers that do the same job: gflow-cli MCP server, Sceneview MCP server and SceneView MCP server.

How does Runway ML compare with other Productivity MCP servers?

safety score 85/100 (higher than 68% of 1,293 Productivity servers); tools 23 (the typical Productivity server has 7); tools that change things 26% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.