Adobe adds AI features and launches a local MCP

Adobe announced new artificial intelligence features for its creative apps at its MAX event in Miami. It also released a local Model Context Protocol (MCP) that lets other chatbots access more features in Creative Cloud apps.

In Firefly, Adobe introduced Builder, a prototyping tool in private beta for creating designs to present ideas. Other additions include tools for making on-brand graphs, editing part of an image without changing other objects, and assembling videos from clips, images, and sound effects. Adobe is also making its creative AI agent proactive and always on, giving it more context about work and allowing it to respond to actions such as removing a background or generating a video thumbnail.

Adobe also announced app-specific features: Photoshop is getting a relighting feature and sliders for prompt-based generative styles; Premiere will get a color-grading system for professionals and an object-removal feature for video; and Lightroom is getting tools to correct blinking eyes and remove blemishes.

The local MCP will expose endpoints and capabilities across Illustrator, Photoshop, After Effects, and Premiere. Adobe vice president Deepa Subramaniam told TechCrunch the company is still deciding what to make available and will use feedback to guide what it exposes. She said Adobe does not want to limit what the MCP endpoint can expose and wants to support users’ creative workflows.

Adobe rival Figma’s co-founder Dylan Field said last month that MCP is not a perfect standard and benefits frontier labs more.