marcellourbani/vscode_abap_remote_fs

VS Code-based Agentic AI Platform for SAP ABAP Development

What it solves

This project provides a bridge between AI assistants and SAP systems, allowing AI to have real-time, live access to ABAP code, tables, and system objects. It eliminates the need for developers to manually navigate complex SAP environments to find code, analyze dependencies, or debug errors, enabling a natural language interface for SAP development.

How it works

The extension connects directly to an SAP system via ADT (ABAP Development Tools) and exposes a set of 40+ specialized tools to AI assistants. It supports GitHub Copilot and other MCP-compatible tools (like Cursor, Claude Code, and Windsurf) by acting as an MCP server. The AI can then autonomously explore the codebase, read function signatures, query tables, and perform tasks like running ATC checks or analyzing runtime dumps.

Who it’s for

ABAP developers and SAP consultants who use VS Code and want to integrate AI-driven automation, autonomous investigation, and modern development workflows (including debugging, testing, and transport management) into their SAP environment.

Highlights

  • Autonomous AI Agent: AI can independently find and analyze objects, such as BAPIs, without manual navigation.
  • MCP Server Support: Extends AI capabilities to non-Copilot tools like Cursor and Claude Desktop.
  • AI Subagents: Specialized agents for discovery, reading, and code review to optimize costs and performance.
  • Deep SAP Integration: Includes embedded SAP GUI, SQL query browser, and a "DVR-style" debug recording and replay feature.
  • Code Quality Tools: Integrated ATC checks, ABAP Cleaner, and distilled "Clean ABAP" coding standards for the AI.
  • Visual Analysis: Generates Mermaid flow diagrams and interactive dependency graphs for ABAP objects.

Related

  • Project
    oisee/vibing-steampunk

    An MCP bridge that gives AI agents and developers full access to SAP ADT APIs and RFC, enabling natural language-driven ABAP development, debugging, and system analysis.

  • Project
    microsoft/DebugMCP

    An MCP server that gives AI coding agents autonomous control over the VS Code debugger to set breakpoints, step through code, and inspect variables.

  • Project
    aws/aws-toolkit-vscode

    A VS Code extension that connects your IDE to AWS resources, enabling developers to manage infrastructure, debug serverless functions, and browse logs without leaving their editor.

  • Project
    OfficeDev/microsoft-365-agents-toolkit

    A Microsoft‑provided toolkit (VS Code/Visual Studio extensions and CLI) that scaffolds, debugs, and deploys AI‑enabled agents, chatbots, and other extensions for Microsoft 365 Copilot, Teams, and Office. It bundles authentication helpers, Azure Functions support, hot‑reload debugging, and CI/CD pipelines, targeting both JavaScript/TypeScript and .NET developers.

  • Project
    microsoft/AI-Engineering-Coach

    A VS Code extension and GitHub Copilot app canvas that analyzes local AI session logs to help developers detect anti-patterns and improve their agentic engineering skills.