MCP-Grounded AI Agentic Development
Code samples embodying this
Prerequisites
- Concept Large Language Models (LLMs) The concept provided is **undefined**, and the supplied sources do not describe a specific, identifiable SAP developer concept by that name. Based on the available snippets — which cover topics such as [Retrieval Augmented Generation (RAG)](https://architecture.learning.sap.com/docs/ref-arch/RA0005/3-retrieval-augmented-generation/readme), prompting LLMs in the generative AI hub, and using custom or small language models on SAP AI Core — no definition can be responsibly constructed for an unnamed or undefined concept. Please provide a valid concept name so that an accurate, source-grounded definition can be written.
- Concept SAP AI Core Service Setup The concept name was not provided, so a precise definition cannot be constructed from the available sources. Based on the sources, these materials collectively cover building and integrating [Generative AI applications](https://architecture.learning.sap.com/docs/golden-path/ai-golden-path/2-build-and-deliver/3-genai-applications/readme) on SAP Business Technology Platform using SAP AI Core — a managed service that developers use to train models, run AI workloads, and connect to large language models via orchestration. Developers leverage it alongside [SAP BTP service instances and keys](https://help.sap.com/docs/btp/sap-business-technology-platform/5b35ee98403045309bb0f8c7f0c79365?locale=en-US&state=PRODUCTION&version=Cloud) to authenticate and consume AI capabilities such as prompt optimization, grounding, multimodal responses, and custom evaluation within their applications.
- Concept Model Context Protocol (MCP) Server Integration **Model Context Protocol (MCP)** is an [open standard that defines how AI models and agents can discover, understand, and interact](https://architecture.learning.sap.com/docs/ref-arch/RA0029/10-third-party-mcp-access/readme) with tools, data sources, and services. Developers use it to expose capabilities — such as SAP BTP account administration or the hana-ml Python library — as MCP endpoints that AI agents can consume in a standardized way. For example, the [HANA AI Toolkit local MCP server](https://architecture.learning.sap.com/docs/ref-arch/RA0033/readme) turns the hana-ml library into an MCP-accessible endpoint, enabling third-party agents and AI models to invoke its functionality without custom integrations.