Mcp Setup logo

Mcp Setup

Community
babamba2
mcp-setup

Guide to install and configure the abap-mcp-adt-powerup MCP server for SAP ADT connectivity

Overview

Publisherbabamba2
Repositorysuperclaude-for-sap
Skill namemcp-setup
Stars
69
Forks
26
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by babamba2 on GitHub. Read the source before you install it.

Installation

Install the Mcp Setup AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/babamba2/superclaude-for-sap/tree/main/skills/mcp-setup
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/babamba2/superclaude-for-sap.git /tmp/superclaude-for-sap
mkdir -p .claude/skills
cp -r /tmp/superclaude-for-sap/skills/mcp-setup .claude/skills/mcp-setup
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mcp Setup in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Mcp Setup on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Mcp Setup is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

SC4SAP MCP Setup

Guides you through installing and configuring the abap-mcp-adt-powerup MCP server, which provides Claude Code with direct connectivity to your SAP system via ABAP Development Tools (ADT) REST APIs. The server exposes 150+ tools covering CRUD for ABAP objects (class, program, CDS, FM, table, etc.) plus runtime, transport, and data-preview operations.

<Response_Prefix> Every response triggered by this skill MUST begin with [Model: <main-model> · Dispatched: <sub-summary>] per ../../common/model-routing-rule.md § Response Prefix Convention. </Response_Prefix>

<Installation_Steps>

  1. Automatic installation (recommended) The MCP server is automatically installed into the plugin's vendor/abap-mcp-adt/ directory during setup:

    bash
    /sc4sap:setup          # full setup wizard (includes MCP install)
    /sc4sap:setup mcp      # MCP install only

    Or via npm:

    bash
    npm run build          # runs tsc + installs abap-mcp-adt into vendor/

    This clones the repo, runs npm install, and builds it. The plugin's .mcp.json is pre-configured to launch bridge/mcp-server.cjs, which delegates to the vendor-installed server.

  2. Configure SAP connection (multi-profile) Connection settings live in a per-system profile, not in a hand-written file:

    • ~/.sc4sap/profiles/<alias>/sap.env — MCP-server env (SAP_URL, SAP_CLIENT, SAP_AUTH_TYPE, SAP_USERNAME, SAP_LANGUAGE, SAP_SYSTEM_TYPE = onprem | cloud, SAP_TIER, blocklist keys). The password is stored in the OS keychain and referenced as SAP_PASSWORD=keychain:sc4sap/<alias>/<user>.
    • <project>/.sc4sap/active-profile.txt — alias of the active profile.

    Create a profile with /sc4sap:setup (wizard Step 4) or /sc4sap:sap-option add; edit it with /sc4sap:sap-option. Do not hand-write sap.env. Key reference and validation rules: ../sap-option/SKILL.md → <Managed_Keys> / <Validation>. Blocklist keys (MCP_BLOCKLIST_PROFILE = minimal | standard (default) | strict | off, MCP_BLOCKLIST_EXTEND, MCP_ALLOW_TABLE) are documented in ../sap-option/SKILL.md → <Managed_Keys> (policy: ../../common/data-extraction-policy.md).

    The bridge resolves the active profile on startup. Process environment variables take precedence over file values.

  3. Verify the connection After restarting Claude Code (or reconnecting MCP via /mcp), run:

    /sc4sap:sap-doctor

    Or manually test by calling GetSession — it should return your SAP system ID, client, and username.

  4. Update the MCP server To update to the latest version:

    bash
    node scripts/build-mcp-server.mjs --update

</Installation_Steps>

<Security_Notes>

  • Never commit a sap.env (profile or legacy .sc4sap/sap.env) to version control. Profiles live under ~/.sc4sap/profiles/, outside the repository.
  • Use process-level environment variables to override sap.env values in CI/CD, so secrets never touch disk.
  • Prefer a read-only SAP user for analysis-only workflows.
  • TLS_REJECT_UNAUTHORIZED=0 is dev-only — never set in production. Install the SAP system certificate into Node.js trust store instead.
  • The MCP server communicates only with the SAP host in SAP_URL. No outbound calls to third parties.
  • Row-extraction on sensitive tables is gated by the blocklist policy above (MCP_BLOCKLIST_PROFILE, MCP_BLOCKLIST_EXTEND, MCP_ALLOW_TABLE). See common/data-extraction-policy.md. </Security_Notes>

<Health_Check> When ARGUMENTS is check / verify / status (case-insensitive), run the vendor pin health check inline and report — do not print the full installation guide.

Execution:

  1. Resolve plugin root (from CLAUDE_PLUGIN_ROOT env; fallback to cache path ~/.claude/plugins/cache/sc4sap/sc4sap/<version>/).
  2. Run: node "<plugin>/scripts/build-mcp-server.mjs" --check
  3. Read the script's exit code and stdout/stderr.
  4. Format the result for the user:
ExitMeaningUser message (follow conversation language)
0 + pinned to <SHA> ✓ on stdoutOK — vendor matches expected pin✅ abap-mcp-adt vendor verified · pinned to <SHA> (truncate to first 12 chars)
0 + pin cannot be verified on stderrWARN — launcher OK, .git stripped (packaged cache install)⚠️ Vendor launcher present, but pin cannot be verified (packaged cache lacks .git). Expected pin: <SHA>. To force a verifiable reinstall: node scripts/build-mcp-server.mjs --update.
1FAIL — vendor missing❌ abap-mcp-adt not installed. Run: node scripts/build-mcp-server.mjs (or /sc4sap:setup mcp).
2FAIL — pin drift❌ abap-mcp-adt vendor drift detected (current HEAD ≠ pinned SHA). Run: node scripts/build-mcp-server.mjs --update.

Output format (single block):

MCP Vendor Health Check
=======================
Status:  <OK|WARN|FAIL>
Pin:     <expected SHA>
Current: <current HEAD or "unverified" or "not installed">
Action:  <user message from table above>

STOP after printing — do not fall through to the full installation guide. </Health_Check>

Task: $ARGUMENTS

Frequently asked questions

What does the Mcp Setup AI skill do?

Guide to install and configure the abap-mcp-adt-powerup MCP server for SAP ADT connectivity

Why use Mcp Setup on TypingMind?

Because you install it once and use it with any model. Mcp Setup is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Mcp Setup in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/babamba2/superclaude-for-sap/tree/main/skills/mcp-setup. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Mcp Setup?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Mcp Setup?

As many as you like. As long as a model supports skills, you can use Mcp Setup with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mcp Setup AI skill free?

Yes. It is published on GitHub by babamba2 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇