Skip to main content

SAP Search MCP Server v2.0

Enterprise MCP server for semantic search over SAP S/4HANA test cases using Azure AI Search.

Features

✅ 2-Tool Architecture - Lightweight summaries + on-demand details
✅ Markdown Tables - Procedure steps in clean table format
✅ Auto-Upload - Documents uploaded automatically on first run
✅ Vector Search - Semantic search using Azure OpenAI embeddings
✅ 240+ SAP Test Cases - S/4HANA 2023 FPS02 Business Process Documents

Quick Start

1. Install

pip install sap-search-mcp

2. Set Environment Variables

Create a .env file:

# Azure AI Search
AZURE_SEARCH_ENDPOINT=https://your-service.search.windows.net
AZURE_SEARCH_KEY=your_key

# Azure OpenAI (for embeddings)
AZURE_SEARCH_OPENAI_ENDPOINT=https://your-openai.cognitiveservices.azure.com/
AZURE_SEARCH_OPENAI_KEY=your_key

# Optional
INDEX_KNOWLEDGEHOUSE=knowledgehouse-en
INDEX_QUERYTABLE=querytable
EMBEDDING_MODEL=text-embedding-3-large

3. Use with Claude Desktop

Edit %APPDATA%\Claude\claude_desktop_config.json:

{
  "mcpServers": {
    "sap-search": {
      "command": "sap-search-mcp",
      "env": {
        "AZURE_SEARCH_ENDPOINT": "https://your-service.search.windows.net",
        "AZURE_SEARCH_KEY": "your_key",
        "AZURE_SEARCH_OPENAI_ENDPOINT": "https://your-openai.cognitiveservices.azure.com/",
        "AZURE_SEARCH_OPENAI_KEY": "your_key"
      }
    }
  }
}

Restart Claude Desktop.

Tools

1. search_sap_test_cases

Search SAP test cases with flexible results.

Single result (full details):

{"prompt": "Create purchase order", "top_k": 1}

Multiple summaries:

{"prompt": "Invoice processing", "top_k": 5}

2. get_test_case_details

Get full procedure table for a specific test case.

{
  "section_header": "Create Purchase Order - ME21N",
  "original_prompt": "purchase order"
}

Example Usage

User: "Show me 5 test cases for sales orders"
→ Returns 5 lightweight summaries

User: "Show me details for option 2"
→ Returns full procedure table in markdown format

Manual Upload (Optional)

Documents are uploaded automatically on first run. To manually re-upload:

sap-search-upload

Development

git clone <repo>
cd sap_search_mcp
pip install -e .
python test.py

What's New in v2.0

  • 🎯 Simplified 2-tool architecture (was 3 tools)
  • 📊 Markdown table formatting for procedures
  • 🚀 Auto-upload on server start
  • ⚡ Lightweight summaries for multiple results
  • 🎨 Better output formatting

License

MIT

Metadata

Release files for sap-search-mcp 2.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for sap-search-mcp 2.0.1
File Size Uploaded Provenance
sap_search_mcp-2.0.1.tar.gz 28.0 MB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for sap-search-mcp 2.0.1
File Interpreter ABI Platform
sap_search_mcp-2.0.1-py3-none-any.whl Python 3 none any Details

Total release size: 56.0 MB

Release files / sap_search_mcp-2.0.1.tar.gz

Download URL sap_search_mcp-2.0.1.tar.gz
Size 28.0 MB
Tags Source
SHA-256 checksum
How to use checksums
6c8b9eb800ac34abdce9ed4d6371702fc89e31bed72aa5ea84a548d57f73abbb
BLAKE2b-256 checksum
How to use checksums
f12374727f313b4ce9e3a83e3071dcde5189ebe9805bbcb258abce7c554c6a14
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.9

Release files / sap_search_mcp-2.0.1-py3-none-any.whl

Download URL sap_search_mcp-2.0.1-py3-none-any.whl
Size 28.0 MB
Tags Python 3
SHA-256 checksum
How to use checksums
3d31d4132431d7a1a69916463779f43113a1efb64791b18043363a81fca27e92
BLAKE2b-256 checksum
How to use checksums
f72e68b2caaa36ab1c1dfb0b5794ad4df8adf3a5ef1c6716e6ac1b77276af4e0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.9

Security for sap-search-mcp 2.0.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page