Adobe launches Model Context Protocol server and new AI features across Creative Cloud apps
New local MCP server exposes Creative Cloud capabilities to external chatbots, while Photoshop, Premiere, and Firefly get AI-powered creative and video tools.
1 source · cross-referenced
- Adobe released a local Model Context Protocol (MCP) server to let external chatbots like ChatGPT, Claude, or Gemini access Creative Cloud features.
- Photoshop, Premiere Pro, and Firefly received new AI-powered creative and video tools, including a prototype builder in Firefly.
- Adobe also added AI agents, relighting, color grading, and object removal features across its Creative Cloud suite.
Adobe announced a new local Model Context Protocol (MCP) server at its MAX 2026 event, allowing external chatbots such as ChatGPT, Claude, or Gemini to access features within Adobe’s Creative Cloud applications like Illustrator, Photoshop, After Effects, and Premiere. Adobe vice president Deepa Subramaniam stated the company is still determining which capabilities to expose and will rely on user feedback to guide future expansions.
The company introduced AI-powered tools across its Creative Cloud suite, including Photoshop, Premiere Pro, and Firefly. Photoshop now includes a relighting feature and sliders for prompt-based generative styles, while Premiere Pro gains a new color grading system for professionals and an object removal feature for video. Lightroom users can correct blinking eyes and remove blemishes with new AI tools.
Adobe expanded Firefly with a prototype builder tool in private beta, positioning it as a competitor to Figma’s design prototyping capabilities. Additional Firefly features include an on-brand graph creation tool, an image editing tool that modifies specific parts of an image without altering others, and an AI-powered video assembly tool that combines clips, images, and sound effects.
Adobe also introduced AI agents designed to be proactive and always-on, providing contextual assistance during creative workflows. The company emphasized enabling quick actions, such as background removal or thumbnail generation, to streamline user tasks.
Adobe highlighted ongoing integrations with third-party AI models from Google, Runway, ElevenLabs, Black Forest Labs, OpenAI, Kling, and ByteDance. Its acquisition Topaz Labs released two new image models: Wonder 4 for upscaling and denoising, and ImageHDR for converting standard images into HDR.
- Nov 11, 2026 · Hugging Face
Hugging Face proposes token pooling-aware training to improve compressed multi-vector retrieval
Trust79 - Nov 11, 2026 · TechCrunch — AI
Fractile raises $720M Series C to develop AI chips and compiler stack
Trust79 - Nov 11, 2026 · The Verge — AI
Google’s Tabletop AI experiment lets users build custom collaborative apps via waitlist
Trust79