Using MCP Servers for AI-Assisted SAP Fiori and SAPUI5 Development

The UI5 Model Context Protocol (MCP) server is a Node.js application written in TypeScript that provides a set of tools to assist AI agents in UI5 application development. The primary goal of this project is to streamline the development process by automating repetitive tasks, providing quick access to UI5 resources, and ensuring adherence to best practices.

For SAP Fiori development, this means that AI support can become more development-aware and more closely aligned with the structures, patterns, and tasks that are relevant in SAP Fiori projects.

In this context, MCP enables AI coding assistants to access dedicated tools, structured context, and development-relevant capabilities. This allows AI-assisted workflows to go beyond generic code suggestions and provide more targeted support for SAP Fiori development scenarios.

The main value is not AI for its own sake. The value lies in making AI support more useful for actual development tasks. For SAP Fiori development, that includes working more effectively with application structures, framework-specific patterns, and guided development flows. This is an inference based on the officially described purpose of the SAP Fiori MCP server and the UI5 MCP server.

The SAP Fiori MCP server is designed to support AI coding assistants in SAP Fiori development scenarios. Its purpose is to enable direct support for creating and editing SAP Fiori applications.

This makes it especially relevant for development tasks at application level. In other words, the SAP Fiori MCP server is focused on helping AI-assisted tooling interact with SAP Fiori applications in a practical and development-oriented way.

The UI5 MCP server complements this by focusing on UI5-specific development support. It provides curated guidance, project-aware context, and development tools for OpenUI5 and SAPUI5 scenarios. It also supports tasks such as scaffolding projects, checking code for deprecated APIs, and identifying the correct API reference for a given version.

This makes the UI5 MCP server particularly relevant when development quality depends on framework-specific knowledge and version-aware implementation guidance.

For SAP Fiori development, both capabilities play distinct but complementary roles.

The SAP Fiori MCP server is centered on direct SAP Fiori application work, especially the creation and editing of SAP Fiori applications. The UI5 MCP server strengthens framework-specific implementation support for SAPUI5 and OpenUI5 development.

Together, these capabilities improve AI-assisted development by combining application-level support with framework-level guidance. This distinction is a careful interpretation of the official SAP positioning of both MCP servers.

These capabilities are relevant in the broader SAP Fiori development toolchain, including SAP Fiori tools and supported development environments such as SAP Business Application Studio and Visual Studio Code. SAP Fiori tools is positioned as a set of extensions that simplifies the creation and modification of SAP Fiori applications.

For local IDE scenarios, UI5 MCP server setup is supported in dedicated workflows. At the same time, there are specific setup limitations in certain remote development scenarios, so implementation planning should always consider the target environment.

MCP-based capabilities extend AI-assisted SAP Fiori development by making AI coding assistants more aware of SAP-specific development context and tools. The SAP Fiori MCP server supports direct work on SAP Fiori applications, while the UI5 MCP server provides UI5-specific development intelligence and guidance. Together, they help make AI-assisted SAP Fiori development more practical, more targeted, and more relevant for real development workflows.

Installing the UI5 MCP server is easy. Head over to the project page and follow the instructions for your code editor (your MCP client): https://github.com/UI5/mcp-server#setup.

Some IDEs (like VS Code) allow you to add MCP servers directly from npm. In that case, choose this option and provide the package name "@ui5/mcp-server" as shown here:

Once installed, the AI agent in your IDE will automatically gain access to the UI5 MCP server and can start using the tools at its own discretion. Depending on your IDE and settings, you may need to approve the first tool calls.

The UI5 MCP server works well for everyday tasks in UI5 projects. It can help you refactor your code and add new features.

In your UI5 projects, try out some prompts like the following:

• "Explain the difference between the sap.ui.require and sap.ui.define APIs"
• "Should I use sap.ui.table.Table or sap.m.List? What is the difference?"
• "How can I style an sap.m.Button to appear as a "reject" action?"

Ask questions about your code:

• "Does this UI5 view apply best practices?"
• "Should I update the UI5 version of this project?"
• "Help me migrate any deprecated UI5 API usage in this UI5 controller"

This release of the UI5 MCP server includes the following six tools, which can be accessed by your AI agent:

Provides curated UI5 development guidelines specifically formatted for AI consumption, ensuring that it follows fundamental concepts and that the generated code adheres to current best practices.

Creates a foundation to start new UI5 projects. The tool comes with templates for both JavaScript and TypeScript UI5 applications. They can be generated as standalone apps or integrated into an existing CAP application.

The templates feature pre-configured OData model setups and follow current best practices.

Allows the AI agent to search the UI5 API reference and learn about API descriptions, signatures, and deprecation information. You may have encountered AI agents hallucinating about UI5 APIs that do not exist. This tool will effectively overcome such problems.

The UI5 MCP server ensures that the version of the API reference matches with the UI5 version configured in your project, so you always get relevant information.

This tool exposes functionality of UI5 linter, allowing the AI agent to scan a UI5 project for problems such as the use of deprecated UI5 APIs, and to apply any fixes provided by UI5 linter.

Beyond these basic linting capabilities, the tool also provides rich contextual information, including rule descriptions, extracts of relevant API references, and even entire guides for the manual migration of certain deprecated APIs that can’t be fixed automatically by UI5 linter. These guides offer step-by-step instructions that guide the agent through complex refactoring, for example when replacing a deprecated, synchronous UI5 API with its modern, asynchronous successor.

Provides selected metadata for your UI5 project. This includes the relevant configuration, the framework version and libraries used, and current information regarding the version’s support status. All this allows the AI agents to quicky gain important insights about the project.

Delivers real-time information about UI5 framework versions, including the support status and upgrade paths.

In its latest version, the UI5 MCP server now also supports the development of UI Integration Cards. The new tools include:

• get_integration_cards_guidelines: Provides dedicated guidelines for the development of UI Integration Cards
• create_integration_card: Creates new UI Integration Cards based on parameters
• run_manifest_validation: Validates the manifest.json, not only for UI Integration Cards, but also of regular UI5 applications and libraries!

For more information on the new tools, see the blog post: UI5 MCP Server Got Extended for UI Integration Cards Generation