What is sap-ai-mcp-servers AGENTS.md?

A guide for maintaining a curated list of SAP-related developer tools, including MCP servers, AI skills, and plugins. The public README is generated from structured data and scripts.

Use it when reviewing submissions, changing catalogue data, updating metadata, or rebuilding the generated README.

It prevents manual edits from being lost and explains how entries are checked, enriched, and published.

How marianfoo/sap-ai-mcp-servers configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to marianfoo/sap-ai-mcp-servers. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/marianfoo/sap-ai-mcp-servers/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/marianfoo/sap-ai-mcp-servers

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/marianfoo/sap-ai-mcp-servers/agents-md/github.svg)](https://agentmods.dev/instructions/marianfoo/sap-ai-mcp-servers/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/marianfoo/sap-ai-mcp-servers/agents-md"><img src="https://agentmods.dev/badge/instructions/marianfoo/sap-ai-mcp-servers/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/marianfoo/sap-ai-mcp-servers/agents-md"><img src="https://agentmods.dev/badge/instructions/marianfoo/sap-ai-mcp-servers/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,512 This file is loaded in full into every session.

When invoked 3,512 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.03512	$0.03512
Opus 5	$0.01756	$0.01756
Sonnet 5	$0.00702	$0.00702
Haiku 4.5	$0.00351	$0.00351

Measured 9d ago against content hash b8d9de1ba022, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sap-ai-mcp-servers AGENTS.md 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 9d 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.

AGENTS.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — LLM Guide for mcp-sap-list

This file explains how the repository works and how to make changes to it correctly. Read this before editing any files.

What this repo does

This is a curated, auto-generated list of SAP-related MCP servers, AI skills, Claude plugins, and adjacent developer tools hosted on GitHub.

The README.md is never edited by hand. It is always generated from structured data via scripts. The pipeline is:

data/catalog.json          ← source of truth for entries
data/overrides.json        ← manual metadata corrections (e.g. license)
         │
         ▼
scripts/enrich-data.mjs    ← fetches live GitHub metadata (stars, license, lastChange)
         │
         ▼
generated/catalog.enriched.json
         │
         ▼
scripts/render-readme.mjs  ← renders README.md from template + enriched data
templates/README.template.md
         │
         ▼
README.md                  ← final output, committed to repo

Run npm run build to execute the full pipeline locally.

Admission and review policy

Review submissions from the evidence in the linked project, not from the style or presumed authorship of the issue or pull request.

LLM-assisted submissions

Assume that many issues, pull requests, READMEs, and project descriptions may be LLM-assisted. LLM use is neither a positive nor a negative admission signal.
Do not reject a submission because its text looks generated, polished, generic, or unusually detailed. Conversely, do not accept claims merely because the submission is comprehensive.
Independently verify material claims against the live repository: project contents, implementation code, manifests, licensing, fork status, current package count/version, and relationship to existing catalog entries.

Public-source requirement for community entries

A Community SAP entry must link to public implementation source for the component being catalogued and that source must carry an applicable open-source license.
A documentation/showcase repository containing only a README, changelog, issue tracker, manifests, Dockerfile, or instructions for installing a closed binary does not satisfy this requirement. A license attached only to a compiled npm/container artifact does not substitute for public implementation source.
Being free to use, published on npm/GHCR, or listed in the MCP Registry is useful distribution evidence, but it is not source-code evidence.
Inspect the repository tree and representative implementation files; do not rely only on GitHub's detected license or the submitter's checklist.

Read the full file on GitHub · 292 lines

Changes

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.

9d ago First seen · 292 lines · 3,512 tokens per session scan A b8d9de1ba022

Subscribe to this mod's changes

sap-ai-mcp-servers AGENTS.md is an instructions file published in the GitHub repository marianfoo/sap-ai-mcp-servers (464 stars, last pushed yesterday), licensed MIT. It adds 3,512 tokens to every session, about $0.0176 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.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

sap-ai-mcp-servers: Instructions file for Codex