Adobe adds AI tools and MCP access across Creative Cloud

Firefly is also gaining features aimed at design and video work. A private-beta prototyping tool called Builder lets users create designs to present ideas, while other additions include on-brand graph creation and image editing that can change one area without affecting other objects. A new AI video tool can assemble clips with elements such as images and sound effects. Adobe said its Firefly creative agent will become proactive and always on, gathering more context about work and offering quick actions such as background removal or video-thumbnail generation.

In Photoshop, Adobe is adding relighting and sliders for prompt-based generative styles. Premiere is getting a professional color-grading system and an object-removal feature for video; Lightroom will offer blinking-eye correction and blemish removal.

Adobe also announced two image models from Topaz Labs, one of its newer acquisitions: Wonder 4 for upscaling and denoising, and ImageHDR for converting standard images to HDR. The company already offers third-party models from providers including Google, Runway, ElevenLabs, Black Forest Labs, OpenAI, Kling and ByteDance.

Adobe has existing ChatGPT and Claude integrations for some product functions. Its new local MCP will expose additional Creative Cloud capabilities. Vice president Deepa Subramaniam told TechCrunch that Adobe is still deciding what to make available and will use feedback from users. “We’re just going to sort-of see how people use it, what they’re trying to do, and keep showing more,” she said. Last month, Figma co-founder Dylan Field said MCP is not a perfect standard and benefits frontier labs more.