Runway
Runway provides generative AI APIs for creating and transforming video, images, audio, avatars, voices, and media workflows.
Verdict
Common use cases
- Prototype video ads from storyboard frames
- Generate placeholder voiceovers for demos
- Create custom sound effects for game prototypes
- Iterate on hero images for landing pages
- Animate product mockups into short clips
Integration
- Vendor
- Runway
- Category
- other
- Auth
- API_KEY
- Tools
- 22
- Composio slug
runway
Tools
- Cancel Task
Cancel a running Runway task or delete its task record. Returns success only when Runway confirms the operation; an already absent task remains a 404 error.
- Create Document
Create a Runway knowledge document from markdown or plain text for reuse by avatar workflows.
- Create Ephemeral Upload
Create only a temporary Runway media upload slot and return its presigned multipart form details and runway:// URI. This action does not upload file bytes; POST them separately to upload_url using fields before using runway_uri.
- Delete Documentdestructive
Permanently delete a Runway knowledge document by its ID.
- Generate Image
Start a Runway text-to-image or reference-guided image generation task and return its task ID and estimated credit cost.
- Generate Sound Effect
Generate an audio effect from a text prompt and return the task ID and estimated credit cost.
- Generate Speech
Synthesize speech with Runway using an exact model-specific voice and option contract, then return the task ID and estimated credit cost.
- Generate Video from Image
Animate one or more input images with a selected Runway model and return the task ID and estimated credit cost.
- Generate Video from Text
Start a Runway text-to-video task with a model-specific typed request and return its task ID and estimated credit cost.
- Get Document
Get one Runway knowledge document, including its full content and the avatars that currently use it.
- Get Organization
Return the connected Runway organization's credit balance, monthly credit spend cap, exact per-model quotas, and current daily generation usage.
- Get Task
Get the current status, cost, output URLs, and failure details for a Runway generation task. Runway does not update a task more often than every five seconds.
- Get Usage
Return daily Runway credit usage by model for an optional UTC date range of up to 90 days.
- Get Workflow
Get a published Runway workflow version and its graph so node IDs and output keys can be inspected before running the workflow.
- Get Workflow Invocation
Get the current status, completed node output URLs, and node or invocation failure details for a Runway workflow invocation.
- List Documents
List Runway knowledge documents one page at a time, with sorting and an opaque continuation cursor. List results omit full document content.
- List Workflows
List the connected account's published Runway workflows and their available versions, ordered as returned by Runway.
- Run Workflow
Invoke a published Runway workflow, optionally overriding graph node outputs, and return the created workflow invocation ID.
- Transform Video
Transform or restyle an existing video with Runway and return the created task ID and estimated credit cost.
- Update Document
Change the name, content, or both for an existing Runway knowledge document. Provide at least one of name or content.
- Upscale Image
Start a Runway image upscaling task and return its task ID and estimated credit cost.
- Upscale Video
Start a Runway video upscaling task and return its task ID and estimated credit cost.
Setup
Setup guide
- 11. Open your Switchy workspace settings and navigate to the Integrations tab. 2. Click 'Add MCP Integration' and select Runway from the catalog. 3. You'll be prompted to paste a Runway API key—log into your Runway account at runwayml.com, go to Settings → API Keys, and generate a new key with full access. 4. Copy the key and paste it into Switchy's configuration modal, then click 'Connect'. 5. Switchy will verify the key and confirm the connection. 6. Open any Project and type '@Runway generate an image of a mountain at sunset' to test—Runway will return a task ID and credit estimate. 7. Use the 'Get Task' tool to check status and retrieve the final asset URL once rendering finishes.
What teammates see: by default, memories from Runway are scoped to the Project (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.
Works well with
Top models
Compatibility data appears once enough Projects have used this MCP together with a given model.
How Switchy teams use it
Starter prompts
Render Hero Image
@Runway generate an image: a sleek electric car parked on a coastal highway at golden hour, cinematic lighting, wide angle
Animate Product Shot
@Runway generate video from the uploaded product image, add a slow 360-degree rotation, 4 seconds long
Synthesize Voiceover
@Runway generate speech: 'Welcome to the platform. Let's walk through your first project setup.' Use a neutral professional voice.
Create UI Sound Effect
@Runway generate a sound effect: a soft, satisfying click with a subtle whoosh tail, 0.5 seconds
Check Render Status
@Runway get the status of task ID abc123 and return the download URL if it's finished
Example outputs
Illustrative - representative of the model's voice and quality, not literal recordings.
@runway generate a 5-second video from this product mockup image using Gen-3 Alpha Turbo, camera zoom-in motion
Started Runway video generation task `tsk_abc123`. Estimated cost: 5 credits. The Gen-3 Alpha Turbo model will animate your product mockup with a zoom-in camera motion over 5 seconds. Typical processing time is 60–90 seconds; you'll receive a runway:// URI once rendering completes. Check task status with the returned ID or wait for the webhook callback if configured.
Demonstrates image-to-video generation, Runway's flagship capability. Requires an active Runway subscription with available credits; the MCP returns a task ID immediately but the video renders asynchronously. You must poll or listen for completion—no blocking wait is built in.
@runway create a knowledge document titled 'Brand Voice Guidelines' from this markdown file so our avatar workflows can reference it
Created Runway document `doc_xyz789` titled 'Brand Voice Guidelines'. The markdown content is now indexed and available to any avatar workflow in your workspace. Avatars can retrieve this document by ID or search for it by title when they need brand tone or messaging rules. Maximum document size is 1 MB; larger files must be chunked or summarized before upload.
Showcases Runway's knowledge-base feature for AI avatar personalization. Useful when you want consistent AI behavior across video or speech tasks. The document persists until explicitly deleted; updates require a new document creation and workflow reconfiguration.
@runway list all my in-progress video tasks and summarize which ones are taking longer than 2 minutes
Found 4 active Runway tasks: `tsk_001` (Gen-3 Alpha, 140s elapsed, still rendering), `tsk_002` (Gen-2, 95s, completing soon), `tsk_003` (Turbo, 45s), `tsk_004` (Gen-3 Alpha, 180s—likely stalled or queued behind capacity). Task `tsk_001` and `tsk_004` exceed the 2-minute threshold. Gen-3 Alpha jobs often queue during peak hours; consider canceling `tsk_004` if urgency matters, or wait for Runway's auto-retry.
Combines task-listing with AI reasoning to surface bottlenecks. Runway does not expose a native 'list tasks' endpoint—this example assumes the MCP tracks task IDs client-side or via webhook logs. Real-world use depends on your task-tracking setup and Runway's API rate limits (10 req/sec).
Use-case deep-dives
When Runway MCP fits rapid creative iteration cycles
A three-person growth team launching a monthly product feature needs hero images, demo videos, and social clips on a two-week sprint. The Runway MCP wins here because it chains text-to-image, image-to-video, and sound-effect generation inside a single Switchy workflow—no context-switching between Runway's web UI and your project tracker. Your AI agent drafts the prompt, generates the asset, checks the task status, and drops the runway:// URI into your Notion doc or Slack thread. The threshold: if your brand guidelines require frame-by-frame approval or you're generating more than 50 assets per sprint, you'll burn credits fast and the async task-polling pattern gets tedious. For teams that prototype visuals in standup and ship the winner by Friday, this MCP collapses three tools into one.
Runway MCP for on-demand tutorial video creation
A five-person support team at a B2B SaaS company fields the same setup questions every week. Instead of screen-recording a new Loom every time the UI changes, they use the Runway MCP to generate short explainer videos from static screenshots and a voiceover script. The agent reads the latest screenshot from your design system, calls Generate Video from Image, synthesizes speech with Generate Speech, and returns a sharable link—all triggered by a Slack command or a new Zendesk ticket tag. This works when your walkthroughs are under 30 seconds and the visuals don't need pixel-perfect accuracy. If you're documenting complex workflows or need captions in six languages, you'll want a dedicated video editor. For repetitive, low-fidelity support content, Runway MCP turns a two-hour task into a two-minute workflow.
When Runway MCP accelerates audio post-production
A two-person podcast team publishes weekly episodes and needs intro music, transition stings, and ambient sound effects that match each episode's theme. The Runway MCP lets them generate custom audio on-demand: the AI agent reads the episode transcript, identifies mood keywords, calls Generate Sound Effect with a tailored prompt, and stages the file for their editor in Descript or Audacity. The 22-tool surface includes ephemeral uploads and task cancellation, so you can batch-generate five variations, pick the best, and delete the rest without leaving Switchy. The limit: if your show has a signature sonic brand or you need stems for remixing, stock Runway audio won't replace a composer. For teams that ship fast and prioritize variety over brand consistency, this MCP turns sound design from a bottleneck into a background task.
Frequently asked
What does the Runway MCP let me do in Switchy?
It lets your team generate images, videos, sound effects, and speech directly from prompts or reference files inside Switchy conversations. You can also manage knowledge documents for avatar workflows and track running tasks. All 22 tools map to Runway's Gen-3, image, and audio APIs, so you get the same output quality without leaving the workspace.
Do I need a paid Runway account to use this MCP?
Yes. You need an active Runway subscription and an API key from your account settings. Free Runway accounts don't issue API keys. Each generation consumes credits from your Runway plan, and the MCP returns the estimated cost before starting a task. Switchy itself doesn't charge extra for the connection.
Can the Runway MCP edit existing videos or remix them?
No. It only generates new assets from scratch—text to image, image to video, text to audio. If you need to trim, splice, or apply effects to existing footage, use Runway's web editor or export the generated file and handle it in another tool. The MCP is for creation, not post-production.
How is this different from just using Runway's web app?
The MCP keeps your entire creative workflow inside Switchy. Your team can prompt, review outputs, and iterate without switching tabs or manually downloading files. It's faster for collaborative projects where the AI conversation and the asset generation happen in the same thread. You lose Runway's timeline UI but gain chat-native speed.
Who on my team should connect the Runway API key?
Whoever owns your Runway subscription and is comfortable sharing the API key with the workspace. That person's credit balance will fund every generation the team triggers through Switchy. If you want usage isolation, create separate Runway accounts and connect them to different Switchy workspaces.