From laptop to production in one command: Docker MCP Gateway + Docker Offload lets you test AI agents locally with 8B models, then seamlessly scale to 30B models in the cloud. Complete guide to production-ready agentic AI deployment with intelligent interceptors and enterprise security.
Docker Offload revolutionizes development by seamlessly extending your local Docker workflow to cloud GPU infrastructure. Same commands, cloud-scale performance. ⚡🚀
Docker MCP Toolkit adds OAuth support and streamlined Integration with GitHub and VS Code
The MCP Gateway is Docker's solution for securely orchestrating and managing Model Context Protocol (MCP) servers locally and in production including enterprise environments.
The MCP Catalog currently includes over 120+ verified, containerized tools, with hundreds more on the way. Docker’s MCP Catalog now features an improved experience, making it easier to search, discover, and identify the right MCP servers for your workflows - all using CLI Interface.
Cross-Origin Resource Sharing (CORS) is a security feature implemented by web browsers to control how web applications can request resources from different domains, ports, or protocols. At its core, CORS enforces the Same-Origin Policy—a fundamental web security concept that prevents a webpage from one domain from accessing resources on
Discover why small language models (SLMs) are becoming the future of agentic AI systems, offering superior efficiency, cost reduction, and operational benefits over large language models (LLMs) in enterprise deployments.
Learn how to set up Gemini CLI with Docker MCP Toolkit for powerful AI-assisted development. Complete guide with step-by-step instructions, benefits, and real-world examples
Docker Desktop 4.42 brings real-time streaming and tool calling to Model Runner, transforming how developers build AI applications locally. No more waiting for responses or cloud dependencies—watch AI generate content token by token with full GPU acceleration on port 12434.
Solving the n8n community's #1 integration challenge with a practical HTTP bridge solution
Whether you're building generative AI applications, experimenting with machine learning workflows, or integrating AI into your software development lifecycle, Docker Model Runner provides a consistent, secure, and efficient way to work with AI models locally.
The shift from prompt engineering to context engineering reflects a broader evolution in how we design, manage, and optimize interactions with large language models (LLMs). While prompt engineering was once hailed as a core skill for leveraging LLMs, the future lies in how we structure and engineer the context in