Abap MCP server

abap-mcp

Make your AI coding agent an expert SAP ABAP & RAP consultant — local by default. No SAP system, no credentials, one command to install.

abap-mcp is a Model Context Protocol server that gives any AI coding agent — Claude Code, GitHub Copilot, Cursor, Codex, Windsurf — real ABAP senses, built on abaplint (the open-source ABAP parser/linter). The agent brings the reasoning; abap-mcp brings ground truth: a deterministic parser, objective scores, and validated generators that keep the AI honest. It works on ABAP source wherever your agent works — a git checkout, an abapGit export, a code review, CI — long before anything reaches a system.

every snippet linted against Clean ABAP as you write (lintabap), every finding explained with its rationale and examples (explainabaprule), and scaffoldrap_bo starts you from a canonical, self-validated RAP business object instead of a blank editor.

• New to ABAP or RAP? Your agent becomes the senior consultant looking over your shoulder:

get a scored, categorized ABAP Cloud readiness report with an A–D tech-debt grade (checkcloudreadiness), a phased migration backlog with efforts and exit criteria (plancloudmigration), an objective before/after verdict on every rework (compareabap), released-API replacements (checkreleased_api), and CI gates that hold the line while the migration proceeds.

• Senior ABAP consultant? It's your assessment and task engine: point your agent at a repo and

The default stdio edition is 100% local: the analysis engine makes zero network calls and reads no user files. Sources go in as text and structured findings come back. The released-API list and abaplint rule data are package-bundled. An optional guarded Streamable HTTP edition makes the same tools available to remote clients such as ChatGPT web; in that mode, source text is sent to the machine you host. See privacy and data handling.

Why this exists

Every other ABAP MCP server is either a bridge to a live SAP system (ADT/RFC — needs credentials, a system, and trust) or a documentation search. But AI coding agents spend most of their time where the files are — editing abapGit repos, reviewing diffs, generating code — long before anything reaches a system. This server gives agents the missing feedback loop at that layer:

• "Does this ABAP parse? Is it clean? How does it perform?" → lint_abap (+ focus packs)
• "Fix this block automatically — casing, obsolete syntax." → fix_abap (deterministic, parser-guaranteed)
• "How far is this classic report from ABAP Cloud? Grade it." → checkcloudreadiness (A–D)
• "Plan the migration — what do we tackle first?" → plancloudmigration (phased backlog)
• "This class has no tests — start me a harness." → scaffoldabapunit (failing-by-default)
• "What depends on what? Migrate which object first?" → getobjectdependencies (+ Mermaid)
• "Did this rework make the code better or worse?" → compare_abap
• "Is MARA a released API? What do I use instead?" → checkreleasedapi
• "Start me a correct RAP business object." → scaffoldrapbo
• "What's in this 4,000-line class? Draw it." → getabapoutline (+ Mermaid)

Install — 60 seconds

Shortened. The full README is on GitHub.