MCP serverMCP servertypeExposes tools to a coding agent over MCP.See every one →What this type is →independently maintainedindependently maintainedoriginPublished by one person or a small company outside SAP. Says nothing about quality; the readings say that.See every one →

AI Core MCP Server

An MCP server that exposes SAP AI Core's APIs as tools, defined entirely in one JSON config file for a proxy, so deployments, configurations and scenarios are managed through an assistant.

Managing an AI Core landscape — deployments, configurations, scenarios — through an assistant instead of the console, with the whole server expressed as configuration for the proxy rather than as code. The smallest of the three configurations, and the clearest illustration of what the engine underneath makes cheap.

Facts

Last pushLicenceMIT

Where it sits

Lives in
Provides
Agent access to your systemsBTPAgent access to your systemscapabilityGiving an AI agent access to the business data, configuration or operations of systems you run through an MCP server. [Serving your application over MCP](capability:mcp-servers) exposes your own service contract; system access reaches the systems behind it, and one implementation may do both. Development assistance belongs to [agent access to your code](capability:agent-code-access).
Requires
odata-mcp-proxyodata-mcp-proxyartifactThe repository is a configuration, not a server: npm start runs the proxy binary against its JSON config, and there is no application code to run without it.

Who is behind it

Wouter LemaireWouter LemairePersonMaintains this
In the atlas: maintains 25, contributes to 39, wrote 18
@lemaiwo
maintainer

Before choosing this

Conditions

PracticalFunctional boundary

Configuration over an API you must already have entitled and provisioned; and the smallest of these repositories, so what it covers is what its config file happens to name.

PolicySAP API Policy 4.2026a§ 1.1, 1.2, 2.2.2from Agent access to your systemsAn MCP server uses SAP APIs to supply tools, resources or data to an agent.
  • § 1.1 Published APIs. Published APIs are made available for the documented purposes identified by SAP, including integration, extensions and data exchange.
  • § 1.2 Non-Published APIs. Customer and third-party applications must not access non-published APIs except where documentation permits it or SAP otherwise authorizes it.
  • § 2.2.2 AI call sequences and data extraction. Outside SAP-endorsed architectures, data services or expressly identified pathways, the policy prohibits specified agentic API use and systematic or large-scale extraction.

MCP does not replace the API's documented-use boundary. Check that every endpoint is published for the intended use and whether the policy's AI-call or extraction provisions apply to the design.

SAP API Policy 4.2026a →

What it declares

Every artifact

Type
MCP server
Origin
Independently maintained

Connections2

By its type: an MCP server is called by an MCP clientcallsdocumentedrequiresWhere AI Core MCP Server runsYour MCP client, actorYour MCP clientAI Core MCP Server, moduleAI Core MCP Serverodata-mcp-proxy, moduleodata-mcp-proxy
SAPnot SAP's, or the project's ownstated in the documentdocumented only

README

quoted from lemaiwo/ai-core-mcp-server under MIT, read
lemaiwo/ai-core-mcp-server/README.mdOn GitHub

AI Core MCP Server

An MCP (Model Context Protocol) server for SAP AI Core, powered by odata-mcp-proxy. It exposes SAP AI Core APIs as MCP tools, allowing AI assistants like Claude to manage your AI Core landscape through natural language.

The entire server is defined through a single JSON config file -- no custom code required.

How It Works

This project uses the odata-mcp-proxy npm package, which maps OData/REST services to MCP tools based on a configuration file. You provide a config describing your APIs and entity sets, and the proxy generates the corresponding MCP tools automatically.

AI Assistant (Claude, Cursor, etc.)
        |
        | MCP Protocol (HTTP or stdio)
        v
  odata-mcp-proxy
        |
        | REST + OAuth2 (via BTP Destination Service)
        v
  SAP AI Core APIs

Think of it like the SAP Application Router -- a ready-made runtime you configure, not code you write.

Exposed AI Core APIs

The config file (ai-core-api-config.json) defines two API groups:

Lifecycle Management (/v2/lm)
ToolOperationsDescription
Scenarioslist, getAI scenarios -- logical groupings of executables that define a ML use case
ScenarioVersionslistVersions of a scenario
Executableslist, getWorkflow templates (training) and serving templates (inference) under a scenario
ModelslistModels available in a scenario (e.g. LLMs in the generative AI hub)
Configurationslist, get, createParameter sets binding a scenario/executable to inputs and hyperparameters
Executionslist, get, create, update, deleteTraining or batch inference runs, tracked through lifecycle states
Deploymentslist, get, create, update, deleteRunning model-serving instances providing real-time inference endpoints
Artifactslist, get, createRegistered references to datasets, models, or files in an object store
ExecutionScheduleslist, get, create, update, deleteCron-based schedules that automatically create executions
Metricslist, deleteTraining and evaluation metrics recorded during executions
MetalistRuntime capabilities, supported features, and API version info
DatasetFilesget, create, deleteUpload, download, and delete files in the object store
Administration (/v2/admin)
ToolOperationsDescription
Repositorieslist, get, create, update, deleteOnboarded git repos containing workflow/serving templates
Applicationslist, get, create, update, deleteArgoCD applications that sync git repo content into AI Core
DockerRegistrySecretslist, create, update, deleteCredentials for pulling private container images
ObjectStoreSecretslist, create, update, deleteCredentials for S3, Azure Blob, GCS, or other object stores
GenericSecretslist, get, create, update, deleteKey-value secrets (API keys, tokens) for executions and deployments
ResourceGroupslist, get, create, update, deleteTenant isolation units that segregate AI assets and workloads
Serviceslist, getService broker registrations exposing AI Core capabilities

Prerequisites

  • Node.js 18+ (20+ recommended)
  • SAP BTP account with SAP AI Core provisioned
  • BTP Destination configured for the AI Core API (AI_CORE) with OAuth2 authentication
  • Cloud Foundry CLI (cf) and MBT Build Tool (mbt) for deployment

Project Structure

ai-core-mcp-server/
├── package.json                # Start script + odata-mcp-proxy dependency
├── ai-core-api-config.json     # API configuration (defines all MCP tools)
├── mta.yaml                    # BTP Cloud Foundry deployment descriptor
├── xs-security.json            # XSUAA OAuth2 configuration
├── default-env.json            # Local dev credentials (gitignored)
└── LICENSE

Getting Started

1. Install dependencies
npm install
2. Configure BTP destination

Create a BTP Destination pointing to the AI Core API:

DestinationURL
AI_COREhttps://api.ai.prod.<region>.aws.ml.hana.ondemand.com

The destination should use OAuth2 client credentials authentication with the AI Core service key.

3. Local development

Create a default-env.json with your BTP service bindings (XSUAA, Destination, Connectivity) to run locally:

npm start

This runs odata-mcp-proxy --config ai-core-api-config.json.

4. Deploy to BTP
npm run build:btp     # Build MTA archive
npm run deploy:btp    # Deploy to Cloud Foundry

The MTA deployment provisions three service instances:

  • Destination (lite) -- resolves API endpoints and manages OAuth2 tokens
  • Connectivity (lite) -- enables secure backend connectivity
  • XSUAA (application) -- handles OAuth2 authentication with role-based access control

Security

The XSUAA configuration (xs-security.json) defines three role templates:

RoleScopesDescription
MCPViewerreadRead-only access
MCPEditorread, writeRead and write access
MCPAdminread, write, adminFull administrative access

OAuth2 redirect URIs are pre-configured for Claude.ai, Cursor, Microsoft Teams, and local development.

Creating Your Own MCP Server

This project demonstrates how easy it is to create a custom MCP server using odata-mcp-proxy. To build your own:

  1. Create a new project and install the dependency:

    mkdir my-mcp-server && cd my-mcp-server
    npm init -y
    npm install odata-mcp-proxy
  2. Add a start script to package.json:

    {
      "scripts": {
        "start": "odata-mcp-proxy --config my-api-config.json"
      }
    }
  3. Define your APIs in a config file (my-api-config.json):

    {
      "server": {
        "name": "my-mcp-server",
        "version": "1.0.0",
        "description": "My custom MCP server"
      },
      "apis": [
        {
          "name": "my-api",
          "destination": "MY_BTP_DESTINATION",
          "pathPrefix": "/api/v1",
          "csrfProtected": true,
          "entitySets": [
            {
              "entitySet": "Products",
              "description": "Product catalog",
              "category": "master-data",
              "keys": [{ "name": "Id", "type": "string" }],
              "operations": { "list": true, "get": true, "create": false, "update": false, "delete": false }
            }
          ]
        }
      ]
    }
  4. Add your mta.yaml, xs-security.json, and BTP Destinations, then deploy. That's it -- no code to write.

License

MIT

MIT, read
Agent access to your systems
  1. mcp-integration-suiteMCP server for the general Integration Suite functions
  2. mcp-is-tpmJava MCP server for Integration Suite Trading Partner Management
  3. calmcpMCP server with read tools over the SAP Cloud ALM APIs
  4. CostingGeek/sap-mcpPython MCP server fetching sales orders from SAP's business data graph
  5. mcp-sap-focusedrunMCP tools over SAP Focused Run's Landscape Management Database
  6. cloud-alm-itsm-mcpMCP server querying installations via the SAP Cloud ALM ITSM API
  7. hana-mcp-serverMCP server for schema discovery and guarded SQL on SAP HANA
  8. sap_analytics_cloud_mcpMCP server for the SAP Analytics Cloud REST API
  9. mcp-sap-cpiMCP server for Cloud Integration runtime: messages, logs, deployment
  10. BTP CF MCP ServerCloud Foundry V3 API on SAP BTP as MCP tools
  11. BTP MCP ServerBTP Core Services as MCP tools with in-chat dashboards
  12. btp-sap-odata-to-mcp-serverExposes S/4HANA or ECC OData services as MCP tools
  13. CI MCP ServerSAP Cloud Integration OData APIs as MCP tools
  14. odata-mcp-proxyConfig-driven proxy turning OData and REST endpoints into MCP tools
  15. sap-pi-mcp-serverMCP server for SAP PI and PO monitoring and directory metadata
  16. sap-bdc-mcp-serverMCP server managing Delta shares in SAP Business Data Cloud
  17. @mariodefe/sap-datasphere-mcpMCP server with forty-five tools across a Datasphere tenant
  18. midasol/sap-mcp-serverPython MCP server for SAP Gateway OData operations
  19. odata_mcp_goGo binary bridging any OData v2 or v4 service to MCP
  20. odata_mcpPython bridge generating MCP tools from OData v2 metadata
  21. sap-bdc-mcpMCP tooling for SAP Business Data Cloud discovery and contracts
  22. mcp-sap-datasphere-serverRead-only MCP server for exploring SAP Datasphere
  23. sac-workbench-mcpMCP server for authoring in SAP Analytics Cloud from an assistant
  24. MCP Server for SAP BTP AdministrationSAP-hosted MCP endpoint for BTP account administration
  25. SAP LeanIX MCP ServerHosted MCP endpoint onto an SAP LeanIX instance
  26. SAP-samples/hana-cli-claude-pluginClaude Code plugin registering hana-cli's MCP server
  27. SAP-samples/hana-developer-cli-tool-exampleDeveloper-centric command line for SAP HANA
  28. cpi-mcp-serverGo MCP server over Cloud Integration packages and integration flows

Details

Sources3
sap-ai-mcp-serversdiscovered herechecked
github.com/lemaiwo/ai-core-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 viasap-ai-mcp-servers
first seen in the atlas
ecosystem and domainbtp, ai-and-agents
History in the atlas3
  1. The concern it answers is reaching into an SAP system from outside, split out of MCP servers on this day; the sentence on the edge is unchanged.
  2. Triaged out of data/crawled/mcp-candidates.json, the sap-ai-mcp-servers sweep. Written from the repository's own README; the catalogue is credited as where it was found and its words are not reused.
  3. First seen.
For your agent
Ref
artifact:lemaiwo-ai-core-mcp-server
JSON
/artifacts/lemaiwo-ai-core-mcp-server.json
MCP
Connecting an agent