MCP Sales Order Server
This TypeScript MCP server exposes two tools for SAP Sales Order operations using the API_SALES_ORDER_SRV OData v2 service.
README
MCP Sales Order Server
This TypeScript MCP server exposes two tools for SAP Sales Order operations using the API_SALES_ORDER_SRV OData v2 service.
Available tools
read_sales_order- Retrieve a specific sales order by ID or list sales orders with optional
$filter,$top, and$skip.
- Retrieve a specific sales order by ID or list sales orders with optional
create_sales_order- Create a new sales order header and deep insert line items using the
to_Itemnavigation property.
- Create a new sales order header and deep insert line items using the
Setup
- Copy the example environment file:
cp .env
- Install dependencies:
npm install
- Start the MCP server:
npm run start:mcp
Environment variables
SAP_API_URL- Full base URL of the SAP OData service (without trailing slash)- 'SAP_API_KEY' - API key from BusinessHub to access sandbox system
Development
npm run build- compile the TypeScript sourcesnpm run start:mcp- run the MCP server withts-node
Architecture Overview
The system is split into three core layers: your desktop AI client, an intermediate bridging server running securely on SAP Business Technology Platform (BTP), and your main SAP backend data source.

[ Claude Desktop App ] (Local PC) │ ▼ (Configured via local standard I/O file) [ SAP CAP MCP Server ] (Hosted on SAP BTP Cloud Foundry) │ ▼ (Uses SAP Cloud SDK & OData Protocol via SAP_API_URL) [ SAP Sales Order API ] (Backend System)
-
Claude Desktop App (The AI Client): Reads a local configuration file on your machine. When you ask it a sales order question, it uses standard inputs/outputs to securely query the bridge server.
-
SAP CAP MCP Server (The Bridge): Runs on SAP BTP Cloud Foundry. It exposes a secure POST /mcp/call API endpoint via server.js that catches commands from the AI.
-
SAP Cloud OData Client SDK: Found inside the core application files, it translates the AI's requests into official SAP-compliant language to safely process data over your secure SAP_API_URL.
Core Libraries & Dependencies
This project relies on two major ecosystems to seamlessly handle both the AI protocol definitions and the secure SAP enterprise connections:
🤖 Model Context Protocol (@modelcontextprotocol/sdk) This official SDK from Anthropic implements the architectural standard that allows LLMs to interact with external data sources and tools. It defines the schemas, tools, and protocols used in index.ts to expose the read_sales_order and create_sales_order capabilities to Claude in a standardized format.
☁️ SAP Cloud SDK (@sap-cloud-sdk/core) SAP’s official software development kit for JavaScript/TypeScript. Utilized heavily inside OdataClient.ts, it automatically abstracts complex enterprise connectivity tasks like managing destinations, payload serialization, and handling authentication headers when interacting with the OData V2/V4 Sales Order API.
Linking Claude to the Server
To point your desktop client to your BTP deployment, add the server setup details to your local Claude configuration profile.
File Path (Windows): %APPDATA%\Claude\claude_desktop_config.json
File Path (Mac): ~/Library/Application Support/Claude/claude_desktop_config.json
Open or create the file and append your connection arguments:
"mcpServers": { "sap-sales-order-mcp": { "command": "node", "args": [ "C:\<path>\sales-mcp-stdio.js" ] }
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.