Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/marianfoo/mcp-sap-docsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/marianfoo/mcp-sap-docs/00-overview)<a href="https://agentmods.dev/rules/marianfoo/mcp-sap-docs/00-overview"><img src="https://agentmods.dev/badge/rules/marianfoo/mcp-sap-docs/00-overview/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/marianfoo/mcp-sap-docs/00-overview"><img src="https://agentmods.dev/badge/rules/marianfoo/mcp-sap-docs/00-overview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00487 | $0.00487 |
| Opus 5.5 | $0.00195 | $0.00195 |
| Sonnet 5.5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
00-overview scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- 00-overview — 88% identical, 6 lines differ
What it actually says
SAP Docs MCP – High-level Overview (Rule)
Use this when asked about "how it works", "where to change X", or "what runs in prod".
System Architecture
- MCP Server: Stdio-based server for Claude/LLM integration
- HTTP Servers: Development server (port 3001) and streamable HTTP server (port 3122)
- Search Pipeline: BM25-only (FTS5) → metadata-driven configuration → formatted results
- Metadata-Driven: All source configurations centralized in
src/metadata.json - Submodule Management: Shallow, single-branch clones with blob filtering for performance
Key Components
- Search: Pure BM25 using SQLite FTS5 for fast, reliable search
- Configuration: Centralized metadata system with type-safe APIs
- Sources: 27 documentation sources (SAPUI5, CAP, ABAP Standard + Cloud, wdi5, Cloud SDK, etc.)
- Tools: 5 MCP tools (search, fetch, sap_community_search, sap_help_search, sap_help_get)
- Build Process: TypeScript compilation → Index building → FTS database creation
- ABAP Integration: Standard + Cloud variants (on-premise + BTP) with intelligent filtering
Production Setup
- Remote Server: Hosted MCP server at https://mcp-sap-docs.marianzeis.de/mcp
- PM2: 3 processes (proxy, http, streamable) via
ecosystem.config.cjs - Deployment: GitHub Actions → SSH → enhanced
setup.sh→ PM2 restart - Health: Multiple endpoints (/status, /health, /healthz, /readyz)
- Submodules: Optimized shallow clones with partial clone filtering
- Protocol: MCP Streamable HTTP (latest protocol) + STDIO support
@file package.json @file src/metadata.json @file src/lib/config.ts @file src/lib/metadata.ts @file src/lib/search.ts @file src/server.ts @file src/http-server.ts @file src/streamable-http-server.ts @file ecosystem.config.cjs @file docs/ARCHITECTURE.md @file docs/DEV.md
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 38 lines · 487 tokens per session scan A 3f43c29c3479
00-overview is a cursor rule published in the GitHub repository marianfoo/mcp-sap-docs (243 stars, last pushed today), licensed Apache-2.0. It adds 487 tokens to every session, about $0.0019 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
shared-plane-packages
Pattern for creating shared plane packages that serve both migration and runtime planes.