@cap-js/mcp-server
Reduces development friction for CAP application teams by enabling AI assistants to understand and operate on CAP-specific code patterns, schemas, and projec…
An MCP server for the SAP Cloud Application Programming Model (CAP). It gives AI assistants two tools: search_model, which fuzzy-searches CDS definitions (entities, services, HTTP endpoints) in your project's compiled model, and search_docs, which searches preprocessed CAP documentation via local vector embeddings. Configure any MCP client — Claude Code, Cline, VS Code Copilot, opencode — to launch it with npx.
- Ask Claude to generate CAP application boilerplate code with proper project structure.
- Generate data model definitions and service handlers for SAP Cloud Application Programming.
- Find and fix common CAP application errors using Claude's understanding of best practices.
Reduces development friction for CAP application teams by enabling AI assistants to understand and operate on CAP-specific code patterns, schemas, and project structure without manual context handoff.
Development teams building SAP Cloud Application Programming model applications seeking faster iteration through AI-assisted coding.
https://github.com/cap-js/mcp-server
By GitHub Actions
How to Get It
npx -y @cap-js/mcp-server
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Once it’s connected, paste this into Claude:
Generate CAP application boilerplate code with proper project structure
Trust Signals Auto-scanned
Data & Access
Community Pulse Quiet
No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 98 GitHub stars; contributors unknown; last commit 6d ago; license Apache-2.0.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 98 GitHub stars; contributors unknown; last commit 6d ago; license Apache-2.0.