Use Runware API through MCP for image, video, audio, 3D, and text tasks.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "io.github.Runware/mcp" MCP server from askskill: Run: claude mcp add 'io-github-runware-mcp' -- npx -y @runware/mcp
Use Runware image capabilities to generate a hero visual for a new product launch poster, with a modern and bright style suitable for social media promotion.
A generated image suited for marketing use, ready for posters or social media assets.
Call the Runware API through MCP to run a batch of image, audio, and text tasks, then return the result for each task.
Results for multiple tasks, suitable for use in an automated workflow.
Use Runware's 3D and video capabilities to prepare a short product showcase video and a basic 3D asset.
Video and 3D outputs for showcasing, prototyping, or creative production.
Developers can connect this MCP tool to AI assistants or automation flows and access image, video, audio, 3D, and text capabilities in one place. This reduces the effort of integrating separate interfaces.
Designers or marketers can use this tool to generate or process different media types for campaign assets, demos, or creative exploration. It fits teams that need cross-modal content output.
It exposes the full Runware API as MCP tools, covering image, video, audio, 3D, and text capabilities. It is suitable for unified use inside MCP-compatible AI environments.
Based on the provided description, it supports image, video, audio, 3D, and text. For more specific interface details, see the source repository.
The provided material does not include installation steps or prerequisite details. Please check the source repository for requirements.
Connect MCP coding tools to RunAPI for multimodal generation across 130+ AI models.
Create GPT Image 2 jobs via MCP and track status and pricing.
Create Runway tasks, monitor status, and check pricing through MCP.
Access 130+ multimodal AI models through one unified API interface.
Add image understanding to AI coding assistants for screenshot-based development analysis.
Understand and generate images and videos for multimodal creation and analysis.