> For the complete documentation index, see [llms.txt](https://docs.umbraco.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.umbraco.com/umbraco-in-ai/readme.md). # Umbraco in AI Learn how AI works in Umbraco with Model Context Protocol (MCP), context engineering, and agent skills. Umbraco in AI depends on more than prompts. It depends on tools, context, and instructions working together. This section introduces the core concepts behind AI-assisted Umbraco workflows. It covers how AI connects to Umbraco, how context shapes output quality, and how agent skills guide coding assistants toward better results. ### Core concepts


Model Context Protocol (MCP)	Learn how MCP connects LLMs to tools, APIs, and structured Umbraco capabilities.	Model Context Protocol (MCP)
Context Engineering	Learn how to shape prompts, tools, and context so models produce better results.	Context Engineering
Agent Skills	Learn how reusable instructions help coding agents apply Umbraco patterns correctly.	Agent Skills

### Why these concepts matter Strong AI output depends on the quality of the system around it. In Umbraco, that means giving the model the right tools, the right context, and the right guidance. When these parts work together, AI can help with content operations, schema planning, technical workflows, and developer productivity. When they do not, output becomes vague, inefficient, or incorrect. ### Explore each topic * [Model Context Protocol (MCP)](/umbraco-in-ai/concepts/model-context-protocol.md): explains how LLMs connect to Umbraco tools, APIs, and external systems. * [Context Engineering](/umbraco-in-ai/concepts/context-engineering.md): explains how to improve reliability by controlling what the model sees. * [Agent Skills](/umbraco-in-ai/concepts/agent-skills.md): explains how agent skills provide reusable instructions for AI coding tools. ### What you will learn * How AI connects to Umbraco through MCP. * How context engineering improves relevance and reduces hallucinations. * How agent skills help AI assistants follow current Umbraco patterns. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.umbraco.com/umbraco-in-ai/readme.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.