MCP Server for SAP OData v4
Allows calling SAP OData v4 actions, such as scheduling background jobs, via MCP-compatible AI clients.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Server for SAP OData v4 schedule a background job to run payroll"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Server for SAP OData v4
An MCP (Model Context Protocol) server that exposes SAP OData v4 actions as AI-callable tools. Designed to be used with MCP-compatible AI clients such as Claude.
Tools
Tool | Description |
| Smoke test — returns a hello message |
| Calls a SAP OData v4 action with a given option |
Related MCP server: SAP OData MCP Server
Setup
Clone the repo:
git clone https://github.com/your-username/mcp.git
cd mcpInstall dependencies:
npm installCopy
.env.exampleto.envand fill in your SAP credentials:
cp .env.example .envBuild the TypeScript source:
npm run buildStart the MCP server:
npm startConfiguration
Variable | Description |
| Base URL of your SAP OData v4 service |
| SAP username |
| SAP password |
| SAP client number (required) |
| OData action path (e.g. |
Requirements
Node.js 18+
A SAP system exposing an OData v4 service
License
ISC
Available Tools
2 toolshelloD
Inputs: no named parameters.
schedule_background_jobD
Inputs: program_name (required), scrambleoption (required), job_name (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
Only two tools with distinct names, so they are unlikely to be confused. However, the lack of descriptions for 'hello' introduces some ambiguity about its purpose.
No consistent naming pattern: 'hello' is arbitrary while 'schedule_background_job' follows a verb_noun structure, indicating a mismatch.
Two tools are grossly insufficient for an SAP OData v4 server, which would typically require many tools for CRUD operations on entities.
The tool set lacks any OData-specific operations (e.g., read, create, update, delete entities), making it severely incomplete for the stated domain.
Related MCP Connectors
Create and manage scheduled, guarded AI agent jobs with built-in quality control and 900+ connectors
Discover, compare, route, and execute machine-accessible capabilities for AI agents.
Discover, plan and run tools across your connected business systems through one OAuth MCP endpoint
Connects AI assistants to TrackingTime for querying time entries, projects, tasks, customers, and team data using natural language.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceTransforms SAP S/4HANA or ECC systems into conversational AI interfaces by exposing OData services as dynamic MCP tools. Enables natural language interactions with ERP data for querying, creating, updating, and deleting business entities.56 npm1MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to integrate with SAP systems via OData REST APIs for querying entity sets, performing CRUD operations, and executing function imports. It features automatic service discovery, CSRF token management, and smart connection handling without requiring the SAP RFC SDK.1113MIT
- AlicenseNot gradedqualityDmaintenanceExposes SAP S/4HANA OData services as tools for LLMs, enabling users to list and create sales orders via the Model Context Protocol. It integrates with SAP BTP using the SAP Cloud SDK to provide secure access to enterprise data through natural language.ISC
- FlicenseAqualityDmaintenanceEnables interaction with SAP S/4HANA systems via OData, allowing service discovery, metadata exploration, field value retrieval, and CRUD operations through natural language.45-