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/20-tools-and-apis)<a href="https://agentmods.dev/rules/marianfoo/mcp-sap-docs/20-tools-and-apis"><img src="https://agentmods.dev/badge/rules/marianfoo/mcp-sap-docs/20-tools-and-apis.svg" alt="Measured on agentmods" 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 | $0.00731 | $0.00731 |
| Opus 5 | $0.00365 | $0.00365 |
| Sonnet 5 | $0.00146 | $0.00146 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
20-tools-and-apis 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 7d 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:
- 20-tools-and-apis — 98% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Tools & HTTP Endpoints (Rule)
For tool schemas, request/response formats, and endpoints.
MCP Tools (5 total)
search: Unified search across all documentation sources (alias:sap_docs_search)fetch: Retrieve specific documents by ID (alias:sap_docs_get)sap_community_search: Search SAP Community posts with full content (max 75k chars per post with intelligent truncation)sap_help_search: Search SAP Help Portal using private APIssap_help_get: Retrieve full SAP Help page content (max 75k chars with intelligent truncation)
Note: Tool names may appear with prefixes depending on MCP client (e.g., mcp_sap-docs-remote_search)
Content Size Limits
- Maximum: 75,000 characters (~18,750 tokens) for SAP Help and Community content
- Algorithm: Intelligent truncation preserving beginning (60%) and end (20%) with clear notice
- Configuration:
CONFIG.MAX_CONTENT_LENGTHinsrc/lib/config.ts - Details: See
docs/CONTENT-SIZE-LIMITS.md
Server Implementations
- Stdio MCP:
src/server.ts- Main MCP server for Claude integration - HTTP Test Server:
src/http-server.ts- Development server (port 3001)- Endpoints:
/status,/healthz,/readyz,/mcp
- Endpoints:
- Streamable HTTP:
src/streamable-http-server.ts- Production HTTP MCP (port 3122)- Endpoints:
/mcp,/health
- Endpoints:
Response Formats
Standard Text Format
- Search Results:
⭐️ **<id>** (Score: <score>)format - Context Detection: Emoji indicators (🎨 UI5, 🏗️ CAP, 🧪 wdi5)
- Source Attribution: Library grouping with clear source identification
ChatGPT/JSON Format
- Search:
{ "results": [{ "id", "title", "url", "snippet", "score" }] } - Fetch:
{ "id", "title", "text", "url", "metadata" } - Structured: Clean JSON for programmatic access and ChatGPT compatibility
Integration Points
- Community: LiQL API (search via MATCHES + post content retrieval)
- SAP Help: Private elasticsearch + metadata + page content APIs
- Local Docs: File system access with URL generation
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.
- 7d ago First seen · 62 lines · 731 tokens per session scan A 426089b8fbb8
20-tools-and-apis is a cursor rule published in the GitHub repository marianfoo/mcp-sap-docs (219 stars, last pushed yesterday), licensed Apache-2.0. It adds 731 tokens to every session, about $0.0037 per session on Opus 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
python
Python best practices and patterns for modern software development with Flask and SQLite.
api-property-optionality-hygiene
Fix ApiProperty/ApiPropertyOptional optionality mismatches in DTO files; use for scheduled batch fixes or DTO edits.
django
Definitive guidelines for writing maintainable, performant, and secure Django applications, emphasizing modern best practices, clear code organization, and efficient patterns.
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
shared-libraries
Shared libraries - condition framework, inventory containers, file-backed DB, itinerary, references.
env-validation-gate
Env validation gate — every app with ≥1 required env var validates its contract at boot via Zod; raw process.env is banned outside the env module. Full pattern in .claude/skills/t2000-env-gate/.