SampleSampletypeA worked example you read or clone. Evidence: it demonstrates, it never provides.See every one →What this type is →by SAPby SAPoriginPublished by SAP itself. A visible facet, never an input to a reading — a dormant official plugin reads exactly like a dormant independent one.See every one →Starting point

SAP-samples/ui5con-2026-fiori-mcp-server

A UI5con hands-on tutorial creating and modifying a Fiori elements application with AI coding assistants, using Cline and Anthropic's Claude 4.5 Sonnet against the MCP servers developed by SAP for Fiori.

Exercises build a CAP project and a Fiori elements list report from an image, enable automatic data loading, add a column and an analytical chart, then modify an object page with a custom section holding a RichTextEditor building block and add a booking-details object page, all through prompts to an AI client rather than hand-written code. A troubleshooting guide alongside the exercises covers what to do when a prompt misfires or an MCP server tool call fails: checking connectivity, separating a CDS compiler error from a SQLite or browser console error, and restoring to a Cline checkpoint when a strategy does not work. It stops at the exercises run inside SAP Business Application Studio with the specific client and model named; it makes no claim about other AI clients or LLMs.

Facts

Last pushLicenceApache-2.0

Where it sits

Lives in
Demonstrates
Agent access to your codeUI5Agent access to your codecapabilityLetting a coding agent read the project or the system you actually have, reach its model, its objects and its checks, and act on it. In file-based environments that works out of the box; complex systems need dedicated access capabilities. Whatever the environment, the agent also needs project- and framework-specific context, so it understands the thing in front of it rather than guessing from what it remembers of its training data. The transport is incidental: an MCP server, a language server or a CLI answer the same question, and what differs between them is how much of the real thing the agent can see. Distinct from [MCP servers](capability:mcp-servers), which is a protocol adapter on your own running service, and from [agent guidance](capability:agent-guidance), which is knowledge handed over as files rather than read from the thing itself.

Who is behind it

SAP SamplesSAP SamplesOrganisationMaintains this
In the atlas: maintains 222
@SAP-samples
maintainervinayhospetePersonContributes to this
In the atlas: contributes to 15
@vinayhospete
1 contributor

What it declares

Every artifact

Type
Sample
Origin
By SAP

As a sample

Form
A tutorial's companion code

Connections1

SAP-samples/ui5con-2026-fiori-mcp-server connectionsSAP-samples/ui5con-2026-fiori-mcp-serverPROVIDES→ demonstrates1demonstrates authoredAgent access to your code

README

quoted from SAP-samples/ui5con-2026-fiori-mcp-server under Apache-2.0, read
SAP-samples/ui5con-2026-fiori-mcp-server/README.mdOn GitHub

REUSE status

Hands-on | Create great UX with AI, SAP Fiori elements and the MCP Server for Fiori

Description

This repository contains the material for the SAP UI5con Hands-on | Create great UX with AI, SAP Fiori elements and the MCP Server for Fiori.


Overview

In this hands-on tutorial you will work through a set of exercises that highlight the benefits and capabilities of the MCP servers developed by SAP to create and modify SAP Fiori applications with the help of AI coding assistants.

You will gain comprehensive knowledge of AI assisted full-stack development, and learn how to use AI Clients to kickstart your SAP Fiori elements agentic application development.

Using AI during Agentic app Development

We are using Cline as AI client within SBAS and Anthropic claude-4.5-sonnet LLM (Large Language Model) throughout the exercises. When developing SAP Fiori applications with LLMs, you may encounter situations where a prompt is not executed as intended, or technical errors occur when calling MCP server tools. Knowing how to approach these issues systematically can save time and prevent disruption. Cline and the choosen LLM are powerful assistants for problem resolution.

General steps in case of issues:

Detailed steps and examples of resolving common issues

  1. Verify connectivity:

    • Check if your machine has network access.
    • Confirm that the MCP server is up and running.
  2. Approach errors systematically

    • Pause before panicking
      • Use natural pauses when the client asks for approval to inspect the current results and chat history.
      • Stop execution with the "Cancel" button. You can always proceed from there with a new prompt
    • Identify the source: Check if the issue is:
      • CDS compiler error
      • SQLite/database error
      • Console/browser runtime error
  3. Using the LLM to solve an issue

    • The LLM occasionally makes mistakes, or forgets required steps leading to error situations
    • But the LLM can read the terminal output and react to API reponses, and correct error visible there
    • Other issues, like from browser console output, can be resolved by copy-pasting the full error message into the chat and ask for a fix in a prompt
    • LLM works best when exact messages are provided rather than manual descriptions.
  4. Use Restore Points if Needed

    • If a solution strategy does not work, you can always restore the files and chat to a previous checkpoint using Cline’s restore functionality.
  5. Don’t be afraid to retry an exercise or step after restoring to a checkpoint.

Exercises

Begin your exercises here. At the end of each section, there is a link to continue to the next section.

Code of Conduct

Please read the SAP Open Source Code of Conduct.

How to obtain support

Support for the content in this repository is available during the actual time of the online session for which this content has been designed. Otherwise, you may request support via the Issues tab.

License

Copyright (c) 2026 SAP SE or an SAP affiliate company. All rights reserved. This project is licensed under the Apache Software License, version 2.0 except as noted otherwise in the LICENSE file.

Apache-2.0, read

Details

Sources3
Added by handdiscovered herechecked
github.com/SAP-samples/ui5con-2026-fiori-mcp-servertree, pushes, contributors, CIchecked
README.mdquoted, and what the entry declareschecked

Sources are graph entities: the same page may back several entries, and an unreachable source flags every row that rests on it.

Compatibility and provenance
discovered viaAdded by hand
first seen in the atlas
ecosystem and domainui5, ai-and-agents
Flavors1
Fiori elements
“kickstart your SAP Fiori elements agentic application development” — SAP-samples/ui5con-2026-fiori-mcp-server — READMEchecked
Contributors1

From the repository’s contributor list, .

History in the atlas1
  1. First seen.
For your agent
Ref
artifact:sap-samples-ui5con-2026-fiori-mcp-server
JSON
/artifacts/sap-samples-ui5con-2026-fiori-mcp-server.json
MCP
Connecting an agent