We’re excited to announce the release of the SAP Fiori MCP server, a new capability that lets AI coding assistants directly create and edit SAP Fiori applications. This marks the next milestone in our AI journey, following the Project Accelerator introduced earlier this year.
What is MCP — and why it matters?
The Model Context Protocol (MCP) is an open standard that standardizes how applications provide context to large language models. MCP is already supported by clients such as Claude, Cline, Cursor, and VS Code allowing AI-powered workflows to interact seamlessly with developer tools.
Introducing the SAP Fiori MCP server
The SAP Fiori MCP server (@sap-ux/fiori-mcp-server) is an open-source node.js module delivered as part of the open-ux-tools repository. It enables developers using AI coding assistants to generate and adapt SAP Fiori elements applications with precision and context awareness.
It is not the only MCP server published by SAP. The CAP MCP server (@cap-js/mcp-server) provides tools to create and modify CAP node.js projects, and the UI5 MCP server (@ui5/mcp-server) allows AI assistants to write SAPUI5 code. Together, these servers provide complementary entry points into different areas of SAP application development, so that AI assistants can seamlessly data models, SAP Fiori applications, and SAPUI5 code.
With the MCP servers in place, you can already try out scenarios such as:
“Please add an SAP Fiori elements list report app to my CAP project.”“Generate a new CAP project and SAP Fiori app based on my_sketch.png.”“Add Flexible Column Layout to the app.”“Enable initial load for the SAP Fiori app.”
⚠️ Note: The SAP Fiori MCP server is currently released in experimental state and subject to rapid change and enhancements.
AI assistants can discover and act on SAP Fiori projects
The first release comes with a set of capabilities designed to let AI assistants both discover and act on SAP Fiori projects. The SAP Fiori MCP server provides tools to generate SAP Fiori elements applications for CAP node.js projects, finds SAP Fiori applications in the workspace, and allows to edit applications and pages inside applications.
To ensure that the AI produces correct results, we propose rules that guide the LLM’s behavior (see rules). These rules cover important aspects such as using proper SAP Fiori elements application patterns, ensuring data models are valid with UUID primary keys, generating sample data consistently, and preferring code-based modifications over screen personalization.
You can configure the server to be directly called with npx or install it globally via npm (see usage). In both cases, it integrates easily into an MCP-enabled client such as Cline.
Example how the SAP Fiori MCP server is used in Cline.
Developers can build apps more quickly using MCP servers
By connecting directly into SAP Fiori projects through MCP, developers gain a much more cost-effective way to experiment with AI support. They can let LLMs execute complex tasks in context—while the built-in functions and rules ensure adherence to SAP Fiori best practices. This reduces the risk of hallucinations, accelerates prototyping, and makes it easier to iterate quickly on new ideas. Since the SAP Fiori MCP server is with other MCP servers like UI5 and CAP, developers can benefit from a consistent AI-driven experience across different parts of the development process.
This is the first step on the MCP journey
The current release is just the first step. We are already working on extending the server with a document search feature that will make guidance from SAP documentation, tutorials, and examples directly available to the LLM. This means that the AI assistant won’t just follow rules embedded in the server but can also draw from the wealth of published learning content.
In addition, the generator functionality, which in the first release is limited to CAP node.js projects, will be expanded to support any suitable OData source. This will significantly broaden the scenarios in which the SAP Fiori MCP server can be applied, giving developers much more flexibility in how they use AI to create and adapt applications.
Try the SAP Fiori MCP server at SAP TechEd 2025
You can experience the SAP Fiori MCP server live at SAP TechEd Berlin. In session CA261 – Create great UX with AI, SAP Design System, SAP Fiori elements, and SAPUI5, we’ll guide you through using AI and MCP to generate applications, adapt them, and extend them with SAPUI5. It’s a hands-on workshop designed to show how these new capabilities come together in practice.
Closing
This release marks the start of a new era in SAP Fiori development, where AI assistants can not only suggest but also execute tasks reliably. With upcoming enhancements like doc search and broader generator support, we’re laying the groundwork for smarter, faster, and more flexible AI-driven development. As an open-source project we also welcome your contributions. We encourage you to report any issues you encounter. Your feedback is invaluable to us.
We can’t wait to see how you experiment with it—and we look forward to meeting you at TechEd!
We’re excited to announce the release of the SAP Fiori MCP server, a new capability that lets AI coding assistants directly create and edit SAP Fiori applications. This marks the next milestone in our AI journey, following the Project Accelerator introduced earlier this year. What is MCP — and why it matters?The Model Context Protocol (MCP) is an open standard that standardizes how applications provide context to large language models. MCP is already supported by clients such as Claude, Cline, Cursor, and VS Code allowing AI-powered workflows to interact seamlessly with developer tools.Introducing the SAP Fiori MCP serverThe SAP Fiori MCP server (@sap-ux/fiori-mcp-server) is an open-source node.js module delivered as part of the open-ux-tools repository. It enables developers using AI coding assistants to generate and adapt SAP Fiori elements applications with precision and context awareness. It is not the only MCP server published by SAP. The CAP MCP server (@cap-js/mcp-server) provides tools to create and modify CAP node.js projects, and the UI5 MCP server (@ui5/mcp-server) allows AI assistants to write SAPUI5 code. Together, these servers provide complementary entry points into different areas of SAP application development, so that AI assistants can seamlessly data models, SAP Fiori applications, and SAPUI5 code.With the MCP servers in place, you can already try out scenarios such as:“Please add an SAP Fiori elements list report app to my CAP project.”“Generate a new CAP project and SAP Fiori app based on my_sketch.png.”“Add Flexible Column Layout to the app.”“Enable initial load for the SAP Fiori app.”⚠️ Note: The SAP Fiori MCP server is currently released in experimental state and subject to rapid change and enhancements.AI assistants can discover and act on SAP Fiori projectsThe first release comes with a set of capabilities designed to let AI assistants both discover and act on SAP Fiori projects. The SAP Fiori MCP server provides tools to generate SAP Fiori elements applications for CAP node.js projects, finds SAP Fiori applications in the workspace, and allows to edit applications and pages inside applications. To ensure that the AI produces correct results, we propose rules that guide the LLM’s behavior (see rules). These rules cover important aspects such as using proper SAP Fiori elements application patterns, ensuring data models are valid with UUID primary keys, generating sample data consistently, and preferring code-based modifications over screen personalization. You can configure the server to be directly called with npx or install it globally via npm (see usage). In both cases, it integrates easily into an MCP-enabled client such as Cline.Example how the SAP Fiori MCP server is used in Cline.Developers can build apps more quickly using MCP serversBy connecting directly into SAP Fiori projects through MCP, developers gain a much more cost-effective way to experiment with AI support. They can let LLMs execute complex tasks in context—while the built-in functions and rules ensure adherence to SAP Fiori best practices. This reduces the risk of hallucinations, accelerates prototyping, and makes it easier to iterate quickly on new ideas. Since the SAP Fiori MCP server is with other MCP servers like UI5 and CAP, developers can benefit from a consistent AI-driven experience across different parts of the development process.This is the first step on the MCP journeyThe current release is just the first step. We are already working on extending the server with a document search feature that will make guidance from SAP documentation, tutorials, and examples directly available to the LLM. This means that the AI assistant won’t just follow rules embedded in the server but can also draw from the wealth of published learning content.In addition, the generator functionality, which in the first release is limited to CAP node.js projects, will be expanded to support any suitable OData source. This will significantly broaden the scenarios in which the SAP Fiori MCP server can be applied, giving developers much more flexibility in how they use AI to create and adapt applications.Try the SAP Fiori MCP server at SAP TechEd 2025You can experience the SAP Fiori MCP server live at SAP TechEd Berlin. In session CA261 – Create great UX with AI, SAP Design System, SAP Fiori elements, and SAPUI5, we’ll guide you through using AI and MCP to generate applications, adapt them, and extend them with SAPUI5. It’s a hands-on workshop designed to show how these new capabilities come together in practice.ClosingThis release marks the start of a new era in SAP Fiori development, where AI assistants can not only suggest but also execute tasks reliably. With upcoming enhancements like doc search and broader generator support, we’re laying the groundwork for smarter, faster, and more flexible AI-driven development. As an open-source project we also welcome your contributions. We encourage you to report any issues you encounter. Your feedback is invaluable to us.We can’t wait to see how you experiment with it—and we look forward to meeting you at TechEd! Read More Technology Blog Posts by SAP articles
#SAP
#SAPTechnologyblog
