CAPSAFE
MCP server for AI-assisted development of CAP applications
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://api.reuse.software/info/github.com/cap-js/mcp-server)
About This Project
A Model Context Protocol (MCP) server for the SAP Cloud Application Programming Model (CAP). Use it for AI-assisted development of CAP applications (agentic coding).
The server helps AI models answer questions such as:
- Which CDS services are in this project, and where are they served?
- What are the entities about and how do they relate?
- How do I add columns to a select statement in CAP Node.js?
Table of Contents
- About This Project
- Requirements
- Setup
- Usage in VS Code
- Usage in Claude Code
- Usage in OpenAI Codex
- Usage in opencode
- CLI Usage
- Available Tools
search_modelsearch_docs- Support, Feedback, Contributing
- Security / Disclosure
- Code of Conduct
- Licensing
- Acknowledgments
Requirements
See Getting Started on how to jumpstart your development and grow as you go with SAP Cloud Application Programming Model.
Setup
Configure your MCP client (Cline, opencode, Claude Code, GitHub Copilot, etc.) to start the server using the command npx -y @cap-js/mcp-server as in the following examples.
Usage in Claude Code
Register the server with Claude Code.
For all projects (user scope):
claude mcp add --scope user cds-mcp -- npx -y @cap-js/mcp-server
For the current project only (local scope, not committed):
claude mcp add cds-mcp -- npx -y @cap-js/mcp-se
be22aabd7092OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-server -- npx -y @cap-js/[email protected]
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (9)
tests/fixtures/project-path/workspace/linked-project
"using { SharedBooks } from '../../shared/model'; service MonorepoService { entity Books as projection on SharedBooks; }""using { SharedBooks } from '../../shared/model'; service ExternalRaceService { entity Books as projection on SharedBooks; }""using { Outside } from '../../outside/model'; service EscapingService { entity Items as projection on Outside; }""using { SECRET_CUSTOMER_TABLE } from '../../private/model'; service LeakingService { entity Items as projection on SECRET_CUSTOMER_TABLE; }"const { default: calculateEmbeddings } = await import('../../lib/calculateEmbeddings.js')@cap-js/ai, @cap-js/sqlite, @huggingface/hub, @modelcontextprotocol/sdk, @sap/cds, prettier
@sap/cds, @cap-js/sqlite, @cap-js/cds-types
Gates applied: no_behavioural_pass.
be22aabd7092full audit observations/trust-audit/mcp-server/cap-js__cap.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | be22aabd7092 | SAFE | B | 89 | first audit |
Questions
What is the CAP MCP server?
MCP server for AI-assisted development of CAP applications
Is CAP safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does CAP need?
No credential environment variables were found in its source, so it appears to need none.
How does CAP run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as sample at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (be22aabd7092), read on 2026-10-07. The repository is watched and re-audited when it changes.