ADT MCP Server

- Python 3.9+
- pip(the Python package installer)
- A running SAP ABAP system with ADT services enabled
- A.envfile in the project root with your SAP connection settings (see below)

git clone https://github.com/<your-org>/<your-repo>.git cd <your-repo>

Transport Options: The server supports multiple transport protocols: STDIO (default), SSE, and Streamable HTTP.

Create and activate a virtual environment

python -m venv .venv source .venv/bin/activate # Linux/macOS .\.venv\Scripts\activate # Windows

Copy the example.env.exampleto.envand fill in your SAP credentials:

For On-Premise Systems (Basic Authentication)

SAP_AUTH_TYPE=basic SAP_URL=https://my.sap.system:443 SAP_CLIENT=100 SAP_USER=YOUR_USER SAP_PASS=YOUR_PASS SAP_VERIFY_SSL=true # Optional timeout configuration (in seconds) SAP_TIMEOUT_DEFAULT=45 # Default timeout (45 seconds) SAP_TIMEOUT_CSRF=15 # CSRF token timeout (15 seconds) SAP_TIMEOUT_LONG=60 # Long operations timeout (60 seconds)

SAP_AUTH_TYPE=jwt SAP_URL=https://your-system.abap.region.hana.ondemand.com SAP_JWT_TOKEN=eyJhbGciOiJSUzI1NiIsImp... SAP_VERIFY_SSL=true # Optional timeout configuration (in seconds) SAP_TIMEOUT_DEFAULT=45 # Default timeout (45 seconds) SAP_TIMEOUT_CSRF=15 # CSRF token timeout (15 seconds) SAP_TIMEOUT_LONG=60 # Long operations timeout (60 seconds)

💡 Tip: Use the included BTP utilities to generate .env files from service keys automatically!

This server now includes comprehensive SAP BTP support with:

- JWT Token Authenticationfor BTP ABAP systems
- Service Key Parsingand analysis
- Automatic .env Generationfrom BTP service keys
- CLI Utilityfor easy configuration management
- Download your service keyfrom BTP cockpit
- Generate .env fileusing the CLI utility:

python btp_env_generator.py --service-key service-key.json --username your-user@company.com --prompt-password

- get_program_source_mcp– Retrieve ABAP program source
- get_class_source_mcp– Retrieve ABAP class source
- get_function_group_source_mcp– Retrieve function group source
- get_function_source_mcp– Retrieve function module source
- get_include_source_mcp– Retrieve include source
- get_interface_source_mcp– Retrieve interface source
- get_structure_source_mcp– Retrieve structure definition
- get_table_source_mcp– Retrieve table definition
- get_table_contents_mcp– Fetch table data (max rows default 100)
- get_package_structure_mcp– Retrieve package metadata
- get_type_info_mcp– Retrieve type information
- get_transaction_properties_mcp– Retrieve transaction properties
- get_search_objects_mcp– Quick search for repository objects
- get_usage_references_mcp– Retrieve where‑used references for any object
- get_cds_source_mcp– Retrieve CDS view source
- get_metadata_extension_source_mcp– Retrieve metadata extension source
- get_sql_query_mcp– Execute freestyle SQL queries
- get_enhancements_mcp– Discover enhancement implementations

- generate_env_from_service_key_file_mcp– Generate .env from service key file
- generate_env_from_service_key_json_mcp– Generate .env from service key JSON
- parse_btp_service_key_mcp– Parse and analyze service keys
- get_btp_connection_status_mcp– Check current BTP configuration

"MCP error -32000: Connection closed" Error

If you get this error when connecting from another directory:
-

Make sure you use the full path to the server:

python /full/path/to/mcp-adt/mcp_server.py

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

An MCP server to help AI assistants to answer questions and generate AccelByte Extend SDK code more effectively .

Local stdio MCP server that lets AI coding agents read and maintain structured architecture, rules, and decisions directly from your repository.

Official Context7 MCP server that brings up-to-date, version-specific library documentation and code examples into AI coding prompts.

Remote, no-auth MCP server providing AI-powered codebase context and answers

Instead of direct calling MCP tools, mcpcode server transforms MCP tool calls into TypeScript programs, enabling smarter, lower-latency orchestration by LLMs.

Help agents automatically write and test stories for your UI components

Official Svelte MCP server, provides docs and suggestions on the generated code.

Supercharge your Agent with Semantic Code Intelligence and save 💰 in the process!