M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionMCP Abap AdtMCP server for SAP ABAP ADT: full CRUD for RAP and classic ABAP, supporting SAP BTP ABAP Cloud and On-Premise ECC/S/4HANA with JWT/XSUAA and service-key auth.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS61 / 100 · C79 / 100 · B
Reliability8 / 2012 / 20
Security and permissions12 / 2018 / 20
Maintenance13 / 2016 / 20
Documentation15 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • ABAP developers and architects
  • RAP developers
  • Team leads and tech leads needing fast repository visibility
  • Teams building RAG/agent workflows for SAP landscapes
  • Engineering teams scaling AI coding agents while controlling spend
  • Platform teams that need auditable, rollback-aware agent execution records
  • Organizations using multiple agents (Claude, Codex, Gemini) under one governed flow
Not for
  • Users without SAP systems
  • Users who require read-only access (this server provides full CRUD)
  • Users relying on unsupported authentication methods
  • Developers who just want a simple code-completion helper without run governance
  • Teams unwilling to accept local JSONL run records with HMAC signing
  • Environments without a supported adapter (Claude/Codex/Gemini CLIs, direct provider, or verifier-only)
Required permissions
  • Requires access to the SAP system URL (SAP_URL)
  • Requires authentication credentials: JWT token (XSUAA) or basic auth username/password
  • Requires an ABAP client number (SAP_CLIENT)
  • Requires transport request privileges for on-premise systems (SAP_MASTER_SYSTEM, SAP_RESPONSIBLE)
  • Can create, read, update, and delete ABAP objects, so needs appropriate permissions in the ABAP system
  • Read/write access to the configured repo root (writable scope restrictable via --allow-path/--deny-path)
  • Ability to invoke the chosen agent CLI (Claude/Codex/Gemini, etc.) and its underlying model account
  • Local disk writes for run records, receipts, and share outputs (share/run-receipt., etc.)
  • Execution of user-configured verifier commands (e.g. npm test)
Risks and side effects
  • AI agents may unintentionally modify or delete ABAP objects if given overly broad permissions
  • Exposed credentials (passwords, JWT tokens) may be leaked if not handled securely
  • Frequent access to SAP systems could cause performance or lock issues
  • Code generation quality may not meet production standards and requires human review
  • Verifier commands are executed; poorly chosen verifier commands carry security risk despite preflight policy checks
  • Cost and token figures may be estimates (labeled with provenance) and should not be treated as settled accounting
  • Receipt integrity must be verified before use as trustworthy evidence; missing rollback evidence is flagged as EVIDENCE_BOUNDARY
  • Policy defaults come from martin.config.yaml and can be overridden by CLI flags; misconfiguration can loosen safety boundaries
Supported clientsClaude DesktopClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools650