sap-abap-mcp: Instructions file for Codex

AGENTS.md

sap-abap-mcp AGENTS.md is an instructions file for Codex, OpenCode from Ciltress/sap-abap-mcp. It costs 3,602 tokens per session, scanned A, original, MIT.

Repository instructions for an MCP server that lets an AI agent read and write SAP ABAP systems through SAP's development tools. ABAP is SAP's programming language, and MCP is a way for an agent to call external tools.

In plain words
What is it for?
Use it when an agent needs to inspect or change ABAP code, call SAP functions, troubleshoot short dumps, find usages, or work with SAP data through this server.
Why use it?
It explains which documentation and conventions an agent must follow when working with SAP ABAP, including authentication, tool selection, locks, and errors.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is Ciltress/sap-abap-mcp's own configuration. It tells Codex and OpenCode how to work on sap-abap-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sap-abap-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Ciltress/sap-abap-mcp. 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/Ciltress/sap-abap-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Ciltress/sap-abap-mcp

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.

agentmods badge for sap-abap-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ciltress/sap-abap-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/ciltress/sap-abap-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ciltress/sap-abap-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ciltress/sap-abap-mcp/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.

agentmods 80×15 button for sap-abap-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ciltress/sap-abap-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ciltress/sap-abap-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,602 This file is loaded in full into every session.
When invoked 3,602 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03602 $0.03602
Opus 5 $0.01801 $0.01801
Sonnet 5 $0.00720 $0.00720
Haiku 4.5 $0.00360 $0.00360

Measured 9d ago against content hash cc523b1501b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sap-abap-mcp AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

sso.ts SPNEGO/Kerberos session bootstrap (curl --negotiate) and injection
AGENTS.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI agents working on this repository. If you are an agent using the running server to work on ABAP, you want docs/MCP-Tools.md instead.

What this is

An MCP server that gives an agent read/write access to an SAP ABAP system over ADT, authenticated with SPNEGO/Kerberos SSO, an X.509 client certificate or an OAuth 2.0 bearer token — none of which involves a password (there is a password mode too, as a last resort). It wraps abap-adt-api and adds one thing ADT cannot do: calling RFC-enabled function modules, over the SAP Gateway JSON-RPC service.

Read these first

Document When you need it
docs/Tool-Router.md Intent to tool, hand-written: "short dump", "where-used", "SE16". The cheapest useful thing to read, and the right first stop when you know the job but not the tool.
docs/Tool-Reference.md Every tool with its arguments, generated from getTools() by npm run docs:tools. Never edit it by hand.
docs/MCP-Tools.md The rules a generator cannot produce: golden-path workflows, ADT URI and lock semantics, the response/error model, a troubleshooting matrix, and the test-suite map. Start here for how the server behaves.
docs/ABAP-Skills.md The bundled ABAP skills, which of them use these tools, and the two traps found while wiring them up.
docs/Development-Skills.md The bundled general engineering skills, and which fit this repo.
docs/JSON-RPC.md The design and protocol record for the RFC path: the wire protocol read from /IWBEP/CL_JSRPC_*, why a batch shares one LUW, and the traps that bite. Read it before touching JsonRemoteFunctionCallHandlers.ts or anything that calls a function module.
docs/Authentication.md All four logon modes and what SAP needs for each, plus how Streamable HTTP hosting (ABAP_MCP_TRANSPORT=http) builds one per-connection session per SAP OAuth token instead of one shared stdio logon, and the three gates in front of it — the origin/host allow-list, the per-session rate limit, and the credential check. Read it before touching sso.ts, certauth.ts, oauth.ts, passwordauth.ts or session.ts, which is the seam they sit behind — in particular why the placeholder password must never reach SAP, and which failures are latched because retrying them would lock a SAP user.

Read the full file on GitHub · 192 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.

  1. 9d ago First seen · 192 lines · 3,602 tokens per session scan A cc523b1501b4

Subscribe to this mod's changes

sap-abap-mcp AGENTS.md is an instructions file published in the GitHub repository Ciltress/sap-abap-mcp (3 stars, last pushed 16d ago), licensed MIT. It adds 3,602 tokens to every session, about $0.0180 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,737 tokens