SAP GUI MCP Server
Drives the real SAP UI (SAP GUI for Windows via COM Scripting, or SAP Web GUI in a Chromium-based browser) for both SAP R/3 and S/4, enabling login, transaction navigation, field entry, button clicks, table reading, screenshots and scripted batch workflows - especially suited for end-to-end testing, visual validation and documentation capture. Includes transaction-specific helpers for e.g. SE16 and ST22 (English, German, Italian logon languages).
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@SAP GUI MCP Server Log into SAP, open transaction VA01, and take a screenshot of the screen"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
SAP GUI MCP Server
An MCP (Model Context Protocol) server for SAP automation. It allows you to control SAP through Claude Desktop, Claude Code, or opencode - via SAP GUI desktop or SAP Web GUI (Chromium-based browser). Because it drives the real SAP UI (not a headless API), it is especially well-suited for end-to-end testing, visual validation, and capturing screenshots for documentation. The MCP server works with both SAP R/3 and S/4.

Try it yourself: this demo is a skill that ships with this repository -
clone it (or copy .claude/skills/readme-demo/ into your project), then ask
your agent to run the readme demo (or invoke /readme-demo in Claude
Code) - it logs into your system, creates a business partner, screenshots
it, and verifies it in SE16. It needs the desktop backend (SAP GUI for Windows
with scripting enabled), because the screenshots are saved via sap_run_script.
COM Desktop API vs. Web GUI
The SAP COM Desktop API is Windows-only and single-threaded at its core, but well tested. This means that after your agent clicks a button, the MCP server has to wait until the GUI responds, which takes some milliseconds that can add up for batch processes. The Web GUI driver is OS-independent but so far lacks the test coverage and maturity of the COM API driver. Its main benefit is that it can run truly async/concurrent workflows, because your agent/MCP client can switch to another browser tab while it waits for the first tab to update after, e.g., a click.
Pairing with other MCPs
You can easily pair this GUI MCP with e.g. an ADT MCP like aibap.mcp.
ADT MCPs and this GUI MCP complement each other in a two-agent vibe-coding setup: one agent writes ABAP via ADT, while a second agent drives this server to test the generated code in the real SAP UI, captures screenshots, and reports failures back.
Batch scripting: the same click journey n times for the token cost of one tool call
Save tokens with sap_run_script! 🚀 Instead of dozens of back-and-forth tool calls, the AI agent can write and execute a single Python script that loops, branches, and collects results - all in one shot. You just describe what you need; the agent generates the script automatically. Perfect for repetitive workflows like reading 50 table rows or bulk-updating fields. Runs in a secure sandbox against the SAP GUI COM API. Desktop backend only. See Capabilities.
Language-specific behaviour for some transactions
The core of this MCP is not language-specific, meaning it generally works with any SAP logon language.
However, there is also built-in support for specific transactions like SE16 or ST22.
These transaction-specific tools only work for certain logon languages, because the MCP server relies on button or column labels, which vary by language.
We support English (EN), German (DE) and Italian (IT).
Under the hood
Are you a developer? Read ARCHITECTURE.md for codebase structure, request flow diagrams, and how to add new transaction tools. The Development Setup section at the bottom of this page covers running from source.
Setup
Pick an installation method below - each one walks you through two things: creating your SAP credentials file (systems.json), optionally using ${env:VAR} placeholders to reference environment variables, and registering the MCP server with your AI client.
Why a separate credentials file? Most MCP servers put SAP credentials directly in the per-project MCP config (env block), which means re-entering them for every project.
Here, credentials and SAP settings live in a single shared file (systems.json) that all Hochfrequenz SAP MCP servers read automatically - so this server and aibap.mcp both work with the same credentials without duplication.
You can store credentials in plain text, but you can also refer to an environment variable.
Choose one of these three approaches:
Where to register the MCP server:
Claude Code - register once for all projects with
claude mcp add --scope user(recommended), or per project in.mcp.jsonin the project root. Each section below shows both.Claude Desktop - add to
claude_desktop_config.json(global config, path varies by OS - shown in each section below)opencode - add to
opencode.jsonin your project root. Each section below includes a ready-to-useopencode.jsonsnippet alongside the Claude Code snippet.
Special characters in passwords stored in a .json file: If your SAP password contains " or \ characters, you must escape them in the JSON config files: " becomes \" and \ becomes \\. For example, pass"word becomes "pass\"word" and do\main becomes "do\\main". Unescaped special characters will silently break the JSON and the MCP server will fail to start.
Windows file extensions: If file extensions are hidden in Windows Explorer, creating .mcp.json via right-click → New → Text File will produce .mcp.json.txt (or .mcp.json.json if you rename). Make sure "File name extensions" is checked in Explorer's View tab, then rename the file.
Download the binary for your platform from GitHub Releases:
Platform | Binary |
Windows (x64) |
|
macOS (Apple Silicon) |
|
Smart App and other Security Tools
Tip
Windows blocks the
.exe? Windows may flag an executable as downloaded from another computer. If you trust the file downloaded from our GitHub Releases, right-click it → Properties (Eigenschaften) → General (Allgemein). Under Security (Sicherheit), check Unblock (Zulassen), then Apply (Übernehmen) and try again.The checkbox only appears when Windows has marked the file as downloaded from another computer. This removes that download block; it does not override Smart App Control. If Smart App Control still blocks execution, contact your IT administrator rather than disabling protection.
Note
The macOS binary supports the WebGUI backend only (browser automation). The desktop backend requires SAP GUI for Windows (COM Scripting) and is not available on macOS.
macOS Gatekeeper: If macOS refuses to run the binary, clear the quarantine attribute:
xattr -c sapwebgui_mcp_macos_arm64_<version>
Choose a backend:
Desktop Backend (SAP GUI) | WebGUI Backend (Browser) | |
Platform | Windows only | Windows, macOS, Linux |
Requires | SAP GUI for Windows | Chrome browser |
Speed | Faster (works directly with SAP GUI) | Slower (works through a web browser) |
Setup | Simpler (just SAP GUI + this tool) | More steps (also needs Chrome browser setup) |
Option A: Desktop Backend (SAP GUI) - recommended for Windows users
Automates SAP GUI directly - no browser needed. Windows only. Uses sapsucker for typed SAP GUI Scripting access.
Prerequisites:
SAP GUI for Windows installed (standard path - the server finds it automatically via Windows registry)
SAP GUI Scripting enabled (one-time setup, see below)
Server side (requires admin/basis team):
Transaction
RZ11→ parametersapgui/user_scripting→ set toTRUEDynamic parameter - no server restart needed, but users must re-login (close and reopen SAP GUI)
Client side (your PC):
Open SAP Logon or any SAP GUI session
Go to Options (via menu bar, tray icon, or press Alt+F12 in a session)
Navigate to Accessibility & Scripting → Scripting (DE: Barrierefreiheit & Skripting → Skripting)
Check "Enable Scripting" (DE: "Skripting aktivieren")
Uncheck "Notify when a script attaches to SAP GUI"
Uncheck "Notify when a script opens a connection"
The two notification checkboxesmust be unchecked. If left checked, every COM connection triggers a modal popup that blocks automation.
Step 1: Create the SAP config file (systems.json)
This file holds your SAP credentials and is shared with aibap.mcp - configure it once and all Hochfrequenz SAP MCP servers will use it.
On Windows, open Windows Explorer and paste this into the address bar:
%USERPROFILE%\.config\sap-mcpCreate the folder if it doesn't exist, then create a file called systems.json inside it. On macOS/Linux, the path is ~/.config/sap-mcp/systems.json.
There are two distinct identifiers per system - don't mix them up:
Concept | Example | Where it's used |
System key (dictionary key) |
|
|
SAP Logon entry ( |
| Must match the bold description in the SAP Logon pad exactly |
The SAP Logon entry is not the 3-character System ID (SID):
What you see in SAP Logon |
| NOT this (SID) |
DEV S/4HANA |
|
|
DEV - ERP Development |
|
|
If the connection_name doesn't match exactly, you'll get "SAP Logon connection entry not found".
{
"default_system": "dev",
"systems": {
"dev": {
"connection_name": "DEV S/4HANA",
"host": "https://your-sap-system:44300",
"client": "100",
"user": "your_username",
"password": "your_password",
"language": "DE"
}
}
}If your SAP system uses a self-signed or internally-signed certificate (common for VPN/intranet systems), add"tls_skip_verify": true to the system entry. Leave it out if your system has a publicly-trusted certificate.
After editingsystems.json, restart Claude Desktop, Claude Code, or opencode for the changes to take effect.
Don't want your password sitting in the file? A system's string fields - connection_name, host, client, user, password, language, oauth2_client_id - may reference an environment variable instead, using ${env:VAR}:
"user": "${env:SAP_DEV_USER}",
"password": "${env:SAP_DEV_PASSWORD}"The file then holds only structure - which systems exist, their hosts and connection names - so it is safe to commit and share with your team, while the credentials come from your environment or password manager. If a referenced variable is unset or empty, the first tool call that needs a credential - sap_login, for instance - fails with an error naming the variable, rather than logging in with an empty password.
See sap-mcp-config for the complete field reference - all optional fields, validation rules, YAML support, ${env:VAR} placeholder rules, and a visual guide to finding your connection_name in SAP Logon.
Step 2: Configure your MCP client
Note the full path to the downloaded.exe. For example, if you saved sapwebgui_mcp_windows_1.5.0.exe to your Downloads folder, the path is C:/Users/YourName/Downloads/sapwebgui_mcp_windows_1.5.0.exe. Always use forward slashes (/) in JSON, not backslashes (\).
Claude Desktop
Add to claude_desktop_config.json. To open the file: press Win+R, type %APPDATA%\Claude, press Enter. If claude_desktop_config.json does not exist, create a new text file with that exact name (make sure it ends in .json, not .json.txt).
{
"mcpServers": {
"sap-desktop": {
"command": "C:/path/to/sapwebgui_mcp_windows_<version>.exe",
"env": {
"BACKEND_TYPE": "desktop"
}
}
}
}Claude Code
Recommended: register once for all projects (user scope). Run this in PowerShell:
claude mcp add --scope user sap-desktop -e BACKEND_TYPE=desktop '--' C:/path/to/sapwebgui_mcp_windows_<version>.exeTogether with systems.json, this is all Claude Code needs - no .mcp.json in any project folder. Two details matter:
Keep the server name (
sap-desktop) before-e. The-eoption accepts several values, so a name placed after it is read as a second environment variable and the command fails witherror: missing required argument 'commandOrUrl'.Keep the quotes around
'--'. If Claude Code was installed through npm,claudeis a PowerShell script, and PowerShell silently drops an unquoted--before passing the arguments on.-ethen swallows the.exepath and the command fails with the same error. This works in PowerShell, bash and zsh (in bash or zsh,'--'and--are equivalent). In cmd.exe, single quotes are not quoting characters, so write a plain--instead.
If Claude Code still starts an old or broken registration instead of the global one, see Claude Code ignores the global registration.
Alternative: per project. Add to .mcp.json in your project root:
{
"mcpServers": {
"sap-desktop": {
"command": "C:/path/to/sapwebgui_mcp_windows_<version>.exe",
"env": {
"BACKEND_TYPE": "desktop"
}
}
}
}opencode
Add to opencode.json in your project root:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"sap-desktop": {
"type": "local",
"command": ["C:/path/to/sapwebgui_mcp_windows_<version>.exe"],
"enabled": true,
"environment": {
"BACKEND_TYPE": "desktop"
}
}
}
}Inopencode.json, you can use either forward slashes (C:/path/to/...) or double-escaped backslashes (C:\\path\\to\\...) in the command path. Single backslashes will break the JSON silently.
Multi-system access (desktop backend only)
Multi-system support is built into systems.json - add multiple systems and the LLM can switch between them:
How it works:
sap_list_connectionsreturns both configured systems (fromsystems.json) and SAP Logon entries (fromSAPUILandscape.xml).sap_login(system_key="qa")logs into a specific system using credentials fromsystems.json.
Configuration: Add multiple systems to your systems.json. The dictionary key (e.g. "dev", "qa") is the system_key you pass to sap_login. The connection_name field must match the SAP Logon entry description exactly:
{
"default_system": "dev",
"systems": {
"dev": {
"connection_name": "DEV S/4HANA",
"host": "https://dev-sap:44300",
"client": "100",
"user": "dev_user",
"password": "dev_pass",
"language": "DE"
},
"qa": {
"connection_name": "QA System",
"host": "https://qa-sap:44300",
"client": "200",
"user": "qa_user",
"password": "qa_pass",
"language": "EN"
}
}
}When sap_login(system_key="qa") is called, it looks up "qa" in systems.json, reads the credentials, and uses the connection_name field ("QA System") to open the matching SAP Logon entry. If the system key is not found, an error is returned listing the available keys.
No Chrome, no browser setup required.
Verify the setup
Before your first prompt, check that the MCP server starts correctly. Open PowerShell and run:
Claude Code:
claude mcp listExpected output:
sap-desktop: C:/path/to/sapwebgui_mcp_windows_<version>.exe ✓ Connectedopencode:
opencode mcp listExpected output:
● ✓ sap-desktop connectedIf you see ✗ Failed or ✗ failed, the most common cause is a wrong path to the .exe in your config file. Double-check the path and that the file exists there. Run opencode mcp debug sap-desktop for more detail.
For Claude Code, with a user-scope registration there is no config file to edit: claude mcp get sap-desktop shows the registered path, and to change it (for example after downloading a new version), run claude mcp remove sap-desktop -s user and add the server again.
Getting started: Restart Claude Desktop, Claude Code, or opencode, then try: "Log me into SAP" or "Run transaction SE16". SAP GUI will open automatically if it is not already running.
Option B: WebGUI Backend (Browser)
Automates SAP Web GUI through Chrome browser automation. Works on all platforms. This is the default - if you don't set BACKEND_TYPE, the server uses WebGUI.
Step 1: Start Chrome with remote debugging
& "C:\Program Files\Google\Chrome\Application\chrome.exe" --remote-debugging-port=9222 --user-data-dir="C:\temp\chrome-debug" --ignore-certificate-errorsChrome path may differ. The path above is for a system-wide Chrome installation. If Chrome was installed only for your user, the path is typically:
& "$env:LOCALAPPDATA\Google\Chrome\Application\chrome.exe" --remote-debugging-port=9222 --user-data-dir="C:\temp\chrome-debug" --ignore-certificate-errorsNot sure where Chrome is installed? See Finding your Chrome path in the Troubleshooting section below.
Step 2: Create systems.json
Create the SAP config file if you haven't already (Windows: %USERPROFILE%\.config\sap-mcp\systems.json, macOS/Linux: ~/.config/sap-mcp/systems.json). See sap-mcp-config for the full field reference and YAML support.
{
"default_system": "dev",
"systems": {
"dev": {
"host": "https://your-sap-server:44300",
"client": "100",
"user": "your_username",
"password": "your_password",
"language": "DE"
}
}
}If your SAP system uses a self-signed or internally-signed certificate (common for VPN/intranet systems), add"tls_skip_verify": true to the system entry. Leave it out if your system has a publicly-trusted certificate.
The WebGUI backend connects directly to thehost URL - there is no SAP Logon application involved, so connection_name is not needed here (unlike the Desktop backend).
The WebGUI URL is derived automatically fromhost as {host}/sap/bc/gui/sap/its/webgui. If your SAP system uses a non-standard WebGUI path, set SAP_URL in the MCP config below.
Step 3: Configure your MCP client
Claude Desktop
Add to claude_desktop_config.json (Windows: %APPDATA%\Claude\claude_desktop_config.json, macOS: ~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"sap-webgui": {
"command": "C:/path/to/sapwebgui_mcp_windows_<version>.exe",
"env": {}
}
}
}Claude Code
Recommended: register once for all projects (user scope). Run this in PowerShell, bash or zsh:
claude mcp add --scope user sap-webgui '--' C:/path/to/sapwebgui_mcp_windows_<version>.exeTogether with systems.json, no .mcp.json is needed in any project folder. On macOS, use the path to sapwebgui_mcp_macos_arm64_<version> instead; the command works unchanged in bash and zsh. Keep the quotes around '--' in PowerShell (in cmd.exe, write a plain --), and if you add environment variables with -e, put them between the server name (sap-webgui) and '--' - see the Desktop backend section for why both matter.
If Claude Code still starts an old or broken registration instead of the global one, see Claude Code ignores the global registration.
Alternative: per project. Add to .mcp.json in your project root:
{
"mcpServers": {
"sap-webgui": {
"command": "C:/path/to/sapwebgui_mcp_windows_<version>.exe",
"env": {}
}
}
}opencode
Add to opencode.json in your project root:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"sap-webgui": {
"type": "local",
"command": ["C:/path/to/sapwebgui_mcp_windows_<version>.exe"],
"enabled": true,
"environment": {}
}
}
}Inopencode.json, you can use either forward slashes (C:/path/to/...) or double-escaped backslashes (C:\\path\\to\\...) in the command path. Single backslashes will break the JSON silently.
GITHUB_PAT is optional - only needed for log_feedback (creates GitHub issues) and abapGit operations with private repos. Add it to the env / environment block only if you need those features.
No Docker, no CDP proxy, no Python required.
Verify the setup
Before your first prompt, check that the MCP server starts correctly. Open a terminal (PowerShell on Windows, Terminal on macOS/Linux) and run:
Claude Code:
claude mcp listExpected output:
sap-webgui: C:/path/to/sapwebgui_mcp_windows_<version>.exe ✓ Connectedopencode:
opencode mcp listExpected output:
● ✓ sap-webgui connectedIf you see ✗ Failed, the most common cause is a wrong path to the .exe. Run opencode mcp debug sap-webgui for more detail.
For Claude Code, with a user-scope registration, claude mcp get sap-webgui shows the registered path; to change it, run claude mcp remove sap-webgui -s user and add the server again.
Getting started: Restart Claude Desktop, Claude Code, or opencode, then try: "Log me into SAP" or "Take a screenshot of the current SAP screen".
This guide gets you running with Docker on Windows - no Python or cloning required.
The setup is similar on macOS, with these differences:
Chrome command:
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9222 --user-data-dir="/tmp/chrome-debug" --ignore-certificate-errorsVerify Chrome:
curl http://localhost:9222/json/versionConfig file location:
Claude Desktop:
~/Library/Application Support/Claude/claude_desktop_config.json
Everything else (Docker setup, CDP proxy, MCP config) is identical.
Prerequisites
Docker Desktop for Windows (download)
Chrome browser
VPN client connected (if your SAP system is on an internal network)
Verify Docker is running:
docker --versionStep 1: Start Chrome with remote debugging
Chrome must be started with special flags to allow automation. Run in PowerShell:
& "C:\Program Files\Google\Chrome\Application\chrome.exe" --remote-debugging-port=9222 --user-data-dir="C:\temp\chrome-debug" --ignore-certificate-errorsChrome path may differ. If Chrome was installed only for your user, replace the path:
& "$env:LOCALAPPDATA\Google\Chrome\Application\chrome.exe" --remote-debugging-port=9222 --user-data-dir="C:\temp\chrome-debug" --ignore-certificate-errorsSee Finding your Chrome path below if the command fails.
Verify it's working:
Invoke-WebRequest -Uri 'http://localhost:9222/json/version' -UseBasicParsingYou should see a JSON response. If you get a connection error, make sure you included the --user-data-dir flag.
Step 2: Set up the CDP proxy
Docker containers can't connect directly to Chrome on your host. The CDP proxy solves this.
Create a folder (e.g., C:\sap-mcp\) and add these two files:
docker-compose.yml
services:
cdp-proxy:
image: nginx:alpine
ports:
- '9223:9222'
volumes:
- ./nginx-cdp-proxy.conf:/etc/nginx/conf.d/default.conf:ro
restart: unless-stopped
networks:
default:
name: sap-mcp-networknginx-cdp-proxy.conf
server {
listen 9222;
resolver 127.0.0.11 valid=30s;
location / {
set $backend "host.docker.internal:9222";
proxy_pass http://$backend;
proxy_set_header Host localhost;
proxy_http_version 1.1;
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection "upgrade";
proxy_read_timeout 3600s;
proxy_send_timeout 3600s;
sub_filter 'ws://localhost/' 'ws://host.docker.internal:9223/';
sub_filter 'ws://localhost:9222/' 'ws://host.docker.internal:9223/';
sub_filter_once off;
sub_filter_types application/json;
}
}Then start the proxy:
cd C:\sap-mcp
docker compose up -dVerify it's running:
docker ps --filter "name=cdp-proxy" --format "table {{.Names}}\t{{.Status}}"Step 3: Configure your MCP client
Required: systems.json with your SAP credentials (see sap-mcp-config and Configuration Reference for the default path per OS). All other env variables are optional. See Configuration Reference for the full list.
GITHUB_PAT is only needed for log_feedback (creates GitHub issues) or abapGit operations. Remove -e GITHUB_PAT=... if you don't need these features.
Choose one of the following options based on which Claude client you use.
Option A: Claude Desktop
Open %APPDATA%\Claude\claude_desktop_config.json and add:
{
"mcpServers": {
"sap-webgui": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--network",
"sap-mcp-network",
"-e",
"BROWSER_MODE=connect",
"-e",
"CDP_URL=http://cdp-proxy:9222",
"-e",
"SAP_URL=https://your-sap-server/sap/bc/gui/sap/its/webgui",
"-v",
"C:/Users/YourName/.config/sap-mcp/systems.json:/home/appuser/.config/sap-mcp/systems.json:ro",
"-e",
"GITHUB_PAT=your_github_pat",
"ghcr.io/hochfrequenz/sapwebgui.mcp:latest"
]
}
}
}Replace:
your-sap-serverwith your SAP server hostnameyour_github_patwith a GitHub Personal Access Token (optional - see note above)C:/Users/YourNamewith your home folder (on macOS, use/Users/YourName/...instead ofC:/Users/YourName/...). Docker treats a mount source that is not an absolute path as the name of a Docker volume, so~does not work here.SAP credentials (user, password, client, language) are read from
systems.json, which is volume-mounted into the container
Option B: Claude Code
Recommended: register once for all projects (user scope):
claude mcp add --scope user sap-webgui '--' docker run -i --rm --network sap-mcp-network -e BROWSER_MODE=connect -e CDP_URL=http://cdp-proxy:9222 -e SAP_URL=https://your-sap-server/sap/bc/gui/sap/its/webgui -v C:/Users/YourName/.config/sap-mcp/systems.json:/home/appuser/.config/sap-mcp/systems.json:ro -e GITHUB_PAT=your_github_pat ghcr.io/hochfrequenz/sapwebgui.mcp:latestEverything after '--' is the Docker command and is passed through unchanged, so the -e flags there are Docker's, not Claude Code's. Keep the quotes around '--' (in cmd.exe, write a plain --; see the Desktop backend section for why). Replace C:/Users/YourName with your home folder; write the path out in full instead of using ~, because how ~ is expanded on the command line depends on the shell. Note that a GITHUB_PAT typed on the command line ends up in your shell history.
If Claude Code still starts an old or broken registration instead of the global one, see Claude Code ignores the global registration.
Alternative: per project. Add to .mcp.json in your project root:
{
"mcpServers": {
"sap-webgui": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--network",
"sap-mcp-network",
"-e",
"BROWSER_MODE=connect",
"-e",
"CDP_URL=http://cdp-proxy:9222",
"-e",
"SAP_URL=https://your-sap-server/sap/bc/gui/sap/its/webgui",
"-v",
"C:/Users/YourName/.config/sap-mcp/systems.json:/home/appuser/.config/sap-mcp/systems.json:ro",
"-e",
"GITHUB_PAT=your_github_pat",
"ghcr.io/hochfrequenz/sapwebgui.mcp:latest"
]
}
}
}Step 4: Start chatting
Restart Claude Desktop/Code and try:
"Log me into SAP"
"Run transaction VA01"
"Take a screenshot"
If it tries e.g. to start a dev-browser or install Chrome, cancel and try to be explicit "log me into sap using the sap web gui mcp".
If Docker Desktop isn't running or you're not logged in (docker login ghcr.io) and never pulled the image, you might get a nonspecific error "1 MCP server failed · /mcp".
You need to be logged in to the GitHub Container Registry (ghcr.io). Being logged in to Docker (for example Docker Hub) alone is not sufficient; you must run docker login ghcr.io.
Try pulling manually if you run into errors:
docker pull ghcr.io/hochfrequenz/sapwebgui.mcp:latestIf the containers started but Chrome (in browser automation mode with CDP enabled) is missing, Claude will likely understand how to login but fail on the first tool call.
For contributors who want to run from source.
Prerequisites
Python 3.11+
Chrome browser with remote debugging (see Step 1 above)
Clone and install
git clone https://github.com/Hochfrequenz/sapwebgui.mcp.git
cd sapwebgui.mcp
# Install uv: https://docs.astral.sh/uv/getting-started/installation/
uv sync --group dev
uv run playwright install chromiumRun tools through uv run ... (not a bare pytest from an older venv).
Run tests
uv run --group tests python -m pytest unittests/ -m "not integration" # unit tests only
uv run --group linting ruff check . # code quality
uv run --group linting ruff format --check . # check formattingRun the MCP server locally
# Set environment variables
$env:SAP_URL = "https://your-sap-server/sap/bc/gui/sap/its/webgui"
$env:BROWSER_MODE = "connect"
$env:CDP_URL = "http://localhost:9222"
# Start the server
run-sapgui-mcp-serverConfigure your MCP client
Required: systems.json with your SAP credentials (see sap-mcp-config and Configuration Reference for the default path per OS). All other env variables are optional.
GITHUB_PAT is only needed for log_feedback (creates GitHub issues) or abapGit operations. Remove it if you don't need these features.
When running Python directly (not in Docker), you don't need the CDP proxy - Python can connect to Chrome on localhost.
Claude Desktop
Add to claude_desktop_config.json (Windows: %APPDATA%\Claude\claude_desktop_config.json, macOS: ~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"sap-webgui": {
"command": "C:/path/to/your/venv/Scripts/run-sapgui-mcp-server.exe",
"args": [],
"env": {
"BROWSER_MODE": "connect",
"CDP_URL": "http://localhost:9222",
"GITHUB_PAT": "your_github_pat"
}
}
}
}Claude Code
Recommended: register once for all projects (user scope):
claude mcp add --scope user sap-webgui -e BROWSER_MODE=connect -e CDP_URL=http://localhost:9222 -e GITHUB_PAT=your_github_pat '--' C:/path/to/your/venv/Scripts/run-sapgui-mcp-server.exeKeep the server name before -e and the quotes around '--' (in cmd.exe, write a plain --; see the Desktop backend section for why). A GITHUB_PAT typed on the command line ends up in your shell history.
If Claude Code still starts an old or broken registration instead of the global one, see Claude Code ignores the global registration.
Alternative: per project. Add to .mcp.json in your project root:
{
"mcpServers": {
"sap-webgui": {
"command": "C:/path/to/your/venv/Scripts/run-sapgui-mcp-server.exe",
"args": [],
"env": {
"BROWSER_MODE": "connect",
"CDP_URL": "http://localhost:9222",
"GITHUB_PAT": "your_github_pat"
}
}
}
}Related MCP server: winagent
Capabilities
Your AI client automatically discovers all individual tools and their schemas dynamically upon connection. At a high level, the server gives your agent:
Drive Any SAP Transaction — Execute transaction codes, fill form fields, click buttons, navigate tabs, read and interact with ALV grids and tables, and handle modal popups and status bar messages.
Transaction Shortcuts — Built-in workflows for common developer and basis tasks: query tables (SE16/SE16N), inspect transports (SE09/SE10), search background jobs (SM37), inspect short dumps (ST22), query application logs (SLG1), maintain table views (SM30), and look up Data Dictionary objects (SE11).
High-Performance Scripting (
sap_run_script) — For bulk operations or complex multi-step workflows, the agent can write and run sandboxed Python scripts against the SAP GUI COM API in a single round-trip instead of dozens of tool calls. (Desktop backend only; sandbox contract exposed viasandbox://sap_run_script).Tree Navigation (
sap_tree_read) — Read or search the already-loaded nodes of any tree control (SPRO IMG, SE80 object tree, SM34 navigation tree, docking-container trees) with a node cap and ancestor paths. Read-only: it never expands or selects. (Desktop backend only.)Visual Validation & Screenshots — Capture screenshots of any SAP screen for documentation, E2E test verification, or human-in-the-loop inspection.
Offline Catalogs — Search transaction codes, tables, classes, and function modules instantly without an active SAP connection.
abapGit & Source Code — Pull abapGit repositories and inspect ABAP report source code. Pulls use the
Z_ABAPGIT_PULL_MCP_SHORTCUTreport on the SAP system. For private repositories, setGITHUB_PATorABAPGIT_PAT.sap_abapgit_pulltakes an optionalbranch(e.g.main,feature/x): it switches the registered repository to that branch persistently (kept only if the pull succeeds) and clears a commit pin; the result'sbranchandsap_abapgit_list_reposshow where the repository is. Instead ofrepo,sap_abapgit_pullacceptskey(the 12-digit repository key fromsap_abapgit_list_repos), the only unique identifier when two repositories share a name or URL; it needs a report version withP_KEY.Multi-Session Management — List, bind, release, close, and detach parallel SAP GUI sessions across concurrent agent tasks (
sap_session_list,sap_session_bind,sap_session_release,sap_session_close,sap_session_detach,sap_session_reset_to_primary). Every session has an origin:opened(created by the server) orattached(a window you already had open). The server never closes an attached session;sap_session_detachdrops a session from the registry and leaves its window open (desktop backend only).Browser Automation (WebGUI) — When using the WebGUI backend, low-level browser actions (click, fill, keyboard, screenshot, DOM snapshot) are available as escape hatches for pixel-level control.
Configuration Reference
SAP Credentials (via systems.json)
SAP credentials (user, password, client, language, host) are configured in systems.json (or systems.yaml), not via server environment variables. See sap-mcp-config for the file format. Override the config file path with SAP_CONFIG_FILE. The language of each system must be DE, EN or IT (case-insensitive; omitted means EN) - these are the languages this server supports, and any other value, such as FR, is rejected when the config is loaded with language must be one of "DE", "EN", "IT". Older versions read SAP_USER, SAP_PASSWORD, SAP_MANDANT, SAP_LANGUAGE, SAP_CONNECTION_NAME and SAP_CREDENTIALS from the MCP config's env block; these are ignored now and can be removed from existing configs.
Individual fields may still be sourced from the environment with an ${env:VAR} placeholder - e.g. "password": "${env:SAP_DEV_PASSWORD}" - which keeps secrets out of the file while the structure stays in it. Placeholders work in connection_name, host, client, user, password, language, oauth2_client_id and the top-level default_system.
An unset or empty variable makes the config invalid, so the first tool call that needs a credential - sap_login, for instance - fails with an error naming the variable, never a silently empty credential. Note that the server itself still starts: config loading is lazy, so the failure surfaces on first use rather than at launch. Tools that only list configuration, such as sap_list_connections, do not fail on an invalid config but report the reason in a config_error field of their result instead of returning a silently empty list; the server instructions carry the same message. Text that only looks like a placeholder is used verbatim, so a typo such as ${SAP_PASSWORD} (missing the env: prefix) becomes your literal password rather than an error - see the placeholder rules for the exact forms.
OS | Default path |
Windows |
|
macOS/Linux |
|
Environment Variables (server-specific)
Variable | Required | Description | Default |
| No |
|
|
| No | Override WebGUI URL (default: derived from |
|
| No | Path to systems.json (see table above for default per OS) | (see above) |
| No | Directory that |
|
| No | Allowed root directories for |
|
| No |
|
|
| No |
|
|
| No | Run browser in headless mode. WebGUI only. |
|
| When | Chrome DevTools Protocol URL. WebGUI only. |
|
| No | Explicit path to Chrome binary. If empty, auto-detected. WebGUI only. |
|
| No | User data directory for auto-launched Chrome. WebGUI only. |
|
| No | Minimum ms between COM calls (prevents overload). Desktop only. |
|
| No | GitHub PAT for | - |
| No | GitHub username for abapGit (falls back to | - |
| No | Repository for feedback issues |
|
| No | Separate PAT for abapGit (overrides | - |
| No | Papertrail syslog host (empty to disable) |
|
| No | Papertrail syslog port |
|
| No | Set to |
|
| No |
|
|
Logging
The server logs to stdout by default using a structured text format. Set LOG_FORMAT=json for machine-readable JSON output.
Papertrail (remote logging)
Remote logging to Papertrail is disabled by default. No telemetry is sent unless you explicitly opt in.
To enable it, set both PAPERTRAIL_HOST and PAPERTRAIL_PORT in your .env file or environment:
PAPERTRAIL_HOST=logs.example.com
PAPERTRAIL_PORT=12345When enabled, tool call names, SAP hostnames, and operational metadata are sent to the configured Papertrail endpoint for monitoring and debugging. No SAP credentials or business data are transmitted.
Each release publishes binaries for Windows and macOS:
Binary | Papertrail default | Intended audience |
| off - no defaults bundled | Public / external users |
| Hochfrequenz endpoint baked in at build time | Hochfrequenz-internal use |
| off - no defaults bundled | Public / macOS (Apple Silicon) users |
Both binaries honour user overrides via .env or environment variables.
Troubleshooting
Finding your Chrome path
The Chrome startup commands in this guide use C:\Program Files\Google\Chrome\Application\chrome.exe - the default path for a system-wide Chrome installation. If you get an error like "The system cannot find the path specified", Chrome is likely installed in a different location.
Common Chrome paths on Windows:
Installation type | Path |
System-wide (all users) |
|
Per-user (current user) |
|
How to find your Chrome path (step by step):
Find your Chrome shortcut (on your desktop or in the Start menu)
Right-click the Chrome shortcut → click Properties
In the Properties window, look at the Target field
Copy the path from that field (everything before any
--flags)
For example, if the Target field shows:
"C:\Users\JaneDoe\AppData\Local\Google\Chrome\Application\chrome.exe"Then your Chrome startup command is:
& "C:\Users\JaneDoe\AppData\Local\Google\Chrome\Application\chrome.exe" --remote-debugging-port=9222 --user-data-dir="C:\temp\chrome-debug" --ignore-certificate-errorsQuick check in PowerShell - this command finds Chrome automatically:
Get-Item "C:\Program Files\Google\Chrome\Application\chrome.exe","$env:LOCALAPPDATA\Google\Chrome\Application\chrome.exe" -ErrorAction SilentlyContinue | Select-Object -First 1 -ExpandProperty FullName"network sap-mcp-network not found"
The CDP proxy isn't running or was never started. Start it:
cd C:\sap-mcp
docker compose up -dChrome connection errors
Make sure Chrome is running with
--remote-debugging-port=9222Make sure you used
--user-data-dir(required, otherwise Chrome joins existing instance)Verify with:
Invoke-WebRequest -Uri 'http://localhost:9222/json/version' -UseBasicParsing
"Cannot connect to CDP proxy"
Check if the proxy is running:
docker ps | Select-String cdp-proxyCheck proxy logs:
docker logs sap-mcp-cdp-proxy-1SAP login fails
Check
SAP_URLis correct and accessible from your browserIf using auto-login, verify credentials are configured in
systems.json(see Configuration Reference)Desktop backend: Make sure the
connection_namefield insystems.jsonmatches the SAP Logon pad description exactly (the bold text, not the SID). Open SAP Logon and compare.Try logging in manually first to verify credentials
Claude Code ignores the global registration
When the same server name is registered in more than one scope, Claude Code uses the entry with the highest precedence: local (stored per project in ~/.claude.json), then project (.mcp.json), then user (the global registration from claude mcp add --scope user). See MCP installation scopes in the Claude Code documentation. A forgotten registration with the same name therefore shadows a correct global one. If it points at a binary that no longer exists, the server fails to connect (for example with CONNECTION_CLOSED).
To find and remove the stale entry (shown for sap-desktop; use sap-webgui for the WebGUI backend):
Run
claude mcp get sap-desktopfrom the project directory. TheScope:line shows which registration Claude Code actually uses.Remove a local-scope entry with
claude mcp remove sap-desktop -s local, or the entry in the project's.mcp.jsonwithclaude mcp remove sap-desktop -s project. Always pass-s: without it,removedeletes the server from whichever scope it finds it in, which may be your global registration. (The-s projectvariant edits the project's possibly shared.mcp.json, so commit that change only if the whole team should lose the entry.)
When cleaning up configs from older versions, you can also drop the old SAP_* credential variables from any env block - see SAP Credentials for the list. Credentials are configured only via systems.json (optionally with ${env:VAR} placeholders). SAP_URL and SAP_CONFIG_FILE are still supported.
Transaction input field (OK-Code field) not visible
On first use of SAP Web GUI, the transaction input field (called "OK-Code field" in SAP) may be hidden. The MCP server tries to enable it automatically, but if that fails, you can enable it manually:
Click the gear icon in the toolbar ("GUI-Aktionen und -Einstellungen" / "GUI Actions and Settings")
Select "Einstellungen..." / "Settings..."
Enable "OK-Code-Feld anzeigen" (Show OK-Code Field)
This is a one-time setting that is saved for subsequent logins.
Tools timeout or hang
SAP Web GUI can be slow. If operations timeout:
Check the Chrome window - is SAP responding?
Try
sap_keepalive_startto prevent session timeoutsCheck Docker container logs:
docker logs <container-id>
"Port 9223 already in use"
Another service is using port 9223. Stop it or change the port in docker-compose.yml:
ports:
- '9224:9222' # Use 9224 insteadDocker image pull fails
If you see "unauthorized" or "access denied" when pulling the image, you need to authenticate with GitHub Container Registry.
Step 1: Create a GitHub Personal Access Token
Go to GitHub Token Settings
Click "Generate new token" → "Generate new token (classic)"
You must use "classic" tokens. Fine-grained tokens don't support container registry access.
Give it a name like "Docker GHCR read"
Set expiration: Choose "Custom" and set to 1 year. You'll need to create a new token and re-login when it expires
Select scope:
read:packages(only this one is needed)Click "Generate token"
Copy the token immediately (starts with
ghp_) - you won't see it again!
Step 2: Login to GitHub Container Registry
docker login ghcr.io -u YOUR_GITHUB_USERNAMEWhen prompted for password:
Paste your Personal Access Token (not your GitHub password)
The password won't show as you type - this is normal
In PowerShell, right-click to paste (Ctrl+V may not work)
You should see: Login Succeeded
Step 3: Pull the image
docker pull ghcr.io/hochfrequenz/sapwebgui.mcp:latestYou only need to do this once per machine. Docker stores your credentials.
Still having issues?
Verify the token starts with
ghp_Try:
docker logout ghcr.iothen repeat Step 2
Architecture
The server supports two backends. Choose one via BACKEND_TYPE.
WebGUI Backend (BACKEND_TYPE=webgui, default):
graph BT
Claude["Claude Desktop / Claude Code"]
MCP["MCP Server (sapguimcp)\nPlaywright for browser automation\nSAP-specific tools"]
CDP["CDP Proxy (nginx)\nOnly needed for Docker"]
Chrome["Chrome\nSAP Web GUI loaded\nPersistent session"]
Claude -- "MCP (stdio)" --> MCP
MCP -- "HTTP / WebSocket" --> CDP
CDP -- "CDP (Chrome DevTools Protocol)" --> ChromeDesktop Backend (BACKEND_TYPE=desktop, Windows only):
graph BT
Claude["Claude Desktop / Claude Code"]
MCP["MCP Server (sapguimcp)\nDesktop backend with COM thread\nSAP-specific tools"]
SAP["SAP GUI for Windows\nCOM Scripting API\nPersistent session(s)"]
Claude -- "MCP (stdio)" --> MCP
MCP -- "COM (pywin32)" --> SAPRelated projects
This server is part of a small ecosystem of SAP + AI tooling:
aibap.mcp- complementary MCP server that talks to SAP via the ADT REST API (read/write source, activate, syntax-check, run unit tests, manage transports). Wheresapgui.mcpdrives SAP through its UI,aibap.mcptalks directly to the ABAP Development Tools HTTP API. The two are designed to coexist and share~/.config/sap-mcp/systems.json.AIBAP_TEMPLATE_REPOSITORY- GitHub template for AI-driven ABAP vibe-coding projects. Documents the two-agent pattern (dev viaaibap.mcp, test / documentation / screenshots viasapgui.mcp) end-to-end.Z_ABAPGIT_PULL_MCP_SHORTCUT- SAP-side ABAP report thatsap_abapgit_pullcalls to pull abapGit repos through the ABAP API. Install it on any SAP system where you want the abapGit pull tools to work.sap-mcp-config- shared config schema forsystems.json, consumed by bothsapgui.mcp(Python) andaibap.mcp(Go).
Contributing
See CONTRIBUTING.md for development setup, testing, and coding standards.
Available Tools
71 toolsbrowser_clickBrowser ClickB
Click an element by CSS selector. BEFORE clicking buttons, use sap_get_shortcuts to check if a keyboard shortcut is available - shortcuts are faster and more reliable than clicks.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: selector (required), session, agent_id. Returns: Result from browser_click tool.
browser_evaluateBrowser EvaluateA
Execute JavaScript in the browser. Use with caution - this has full access to the page context. Prefer SAP-specific tools when available. Returns: JSON-serialized result.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: script (required), session, agent_id. Returns: Result from browser_evaluate tool.
browser_fillBrowser FillA
Fill a single input field by CSS selector. For filling multiple fields on the same screen, use sap_fill_form instead - it fills all fields in a single call, which is much faster.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: value (required), selector (required), session, agent_id. Returns: Result from browser_fill tool.
browser_get_htmlBrowser Get HtmlA
Get HTML content of an element or the full page. For large HTML (>50KB), returns a File to avoid context bloat. Prefer sap_get_screen_text or sap_get_form_fields for structured SAP data. Args: selector = CSS selector (None for full page), outer = include element itself (outerHTML) or just children (innerHTML).
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: outer, session, agent_id, selector.
browser_keyboardBrowser KeyboardA
Send keyboard input (key press or text typing). Important: For SAP shortcuts like Ctrl+S, prefer sap_press_key which auto-reads the status bar! For filling multiple form fields, use sap_fill_form - much faster. Args: key = key to press (e.g., 'Enter', 'Tab', 'F3'), text = text to type character by character.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: key, text, session, agent_id. Returns: Result from browser_keyboard tool.
browser_screenshotBrowser ScreenshotA
⚠️ WRONG TOOL — use browser_snapshot instead. browser_snapshot returns a compact text-based accessibility tree that is sufficient for 95% of use cases.
ONLY use browser_screenshot when:
The user EXPLICITLY asks for a screenshot
You need to verify visual rendering/layout issues that cannot be diagnosed from the accessibility tree
This tool returns a large image that rapidly fills up conversation context and degrades performance.
Args: full_page = capture entire scrollable page, selector = optional CSS selector to capture specific element.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: session, agent_id, selector, full_page.
browser_select_optionBrowser Select OptionA
Select an option from a dropdown/select element. For SAP dropdowns, prefer sap_fill_form or sap_set_field which handle SAP-specific dropdown behavior. Args: selector = CSS selector for select element, value = option value to select, label = option text (alternative to value).
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: selector (required), label, value, session, +1 more. Returns: Result from browser_select_option tool.
browser_snapshotBrowser SnapshotA
Get accessibility tree snapshot of the current page. Returns a YAML representation of the ARIA tree - useful for understanding page structure when other tools fail. Args: selector = optional CSS selector to scope the snapshot.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: session, agent_id, selector. Returns: Result from browser_snapshot tool.
browser_waitBrowser WaitA
Wait for an element to reach a specific state. IMPORTANT: Only useful with a selector - calling without a selector is pointless because MCP round-trip time already provides natural delays. Good uses: wait for element to appear (state='visible') or loading spinner to disappear (state='hidden'). Args: selector = CSS selector to wait for, timeout = max wait in ms, state = 'visible'/'hidden'/'attached'/'detached'.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: state, session, timeout, agent_id, +1 more. Returns: Result from browser_wait tool.
chooseChooseA
Present the user with a set of options to choose from.
Call this tool when you need the user to make a decision between discrete alternatives. Use it proactively — don't ask the user to type their choice in chat when you can present clean, clickable options instead.
The user will see a card with one button per option. When they click one, their choice appears as a message in the conversation (as if the user typed it), like:
"Which deployment strategy?" — I selected: Blue-greenIMPORTANT: After calling this tool, you MUST stop and wait for the user's response. Do not continue or take any other actions until you see the "I selected:" message.
Inputs: prompt (required), options (required), title.
log_feedbackLog FeedbackA
Log technical feedback about tool usage patterns, friction points, or optimization opportunities. ENCOURAGED whenever you notice something that could improve tooling. If GITHUB_PAT configured, auto-posts as GitHub issue. BE DETAILED: include transaction code, steps to reproduce, tool names, selectors, timing observations, what you tried, error messages. TAGS: 'tool-combination' (tools always used together), 'repetition' (same tool repeated), 'selector' (hard to find), 'timing' (slow/timeout), 'workflow' (could be simplified), 'missing-tool', 'error-handling', 'deadlock' (got stuck), 'problem' (blocked progress). Use markdown formatting: backticks for code, bold for emphasis.
Inputs: feedback (required), tags. Returns: Result from log_feedback tool.
log_intentLog IntentA
MANDATORY: Log intent when using SAP. You MUST call this at the start of every SAP task and before any SAP write operation. Required for compliance and accountability. WHEN TO CALL: (1) ALWAYS at the start of every SAP-related user request, (2) ALWAYS before any SAP write operation (create, update, delete, post), (3) At milestones during multi-step workflows (e.g., 'Order 3 of 10'), (4) Before running transactions that modify data. Args: intent = high-level description (e.g., 'User requested to create sales order'), context = optional dict (e.g., {'tcode': 'VA01', 'customer': '12345'}).
Inputs: intent (required), context. Returns: Result from log_intent tool.
sap_abapgit_list_reposabapGit List RepositoriesARead-onlyIdempotent
List registered abapGit repositories with their metadata. Returns repo names, Git URLs, packages, branches, last pull timestamps and (when the report provides it) the repository key, plus total_count and matched_count. Use name/package/url/key to filter instead of listing everything (a system can have hundreds of repositories): name, package and url are case-insensitive substrings, or globs when they contain * or ?; key is an exact match, digits, zero-padded to 12; all given filters must match. compact=True returns only name, package and key. Use this to discover the correct repo name before calling sap_abapgit_pull.
Inputs: key, url, name, compact, +3 more. Returns: Result of listing registered abapGit repositories.
sap_abapgit_pullabapGit PullADestructiveIdempotent
Pull changes from a remote git repository using abapGit API. WARNING: overwrites local ABAP objects. Select the repository by repo (name/URL) or by key (from sap_abapgit_list_repos), not both. If a transport is required the error says so: retry with trkorr=... If 'status unknown', the pull may have run: check the last pull time before retrying. Optional branch switches the repository to that branch persistently (kept only if the pull succeeds) and clears a commit pin.
Inputs: key, pat, repo, branch, +4 more. Returns: Result for abapGit actions (pull, stage, diff, check). Use factory methods for…
sap_breakpoint_deleteSap Breakpoint DeleteA
Delete an external ABAP breakpoint on a specific line of a program, class method, or function module. Desktop backend only.
Provide either line_number (1-indexed SAP display line) or match_pattern (substring or regex matched against source lines).
If the line has no breakpoint, SAP sets one. This tool detects that and re-applies to undo it, then reports action='was_not_set'.
Note: this only removes the breakpoint from the source editor. It does NOT step or continue a debugger that is currently stopped and showing a modal dialog — there is no tool for that; only a human at the SAP GUI can dismiss it.
Inputs: object_name (required), object_type (required), session, agent_id, +3 more. Returns: Result of sap_breakpoint_delete.
sap_breakpoint_listSap Breakpoint ListARead-onlyIdempotent
List all external ABAP breakpoints for the current user on a program, class method, or function module. Desktop backend only.
Opens 'Hilfsmittel > Breakpoints > Anzeigen...' dialog in the source editor, reads the grid, and returns matching breakpoints.
Note: if this session is currently stopped at a breakpoint, this tool fails with an error naming the ABAP debugger instead of opening the dialog — continue or exit the debugger in SAP GUI first.
Inputs: object_name (required), object_type (required), session, agent_id, +1 more. Returns: Result of sap_breakpoint_list.
sap_breakpoint_setSap Breakpoint SetADestructive
HIGHLY DANGEROUS — DO NOT CALL unless a human user has explicitly asked for a breakpoint to be set. Live-verified (issue #791): once the breakpoint fires, the SAP session stops and SAP GUI opens the ABAP debugger. The call that triggered it and every later call on that session fail after a few seconds with an error naming the debugger, as can slow calls on other sessions of the same SAP connection; sessions of other connections are not affected. The session works again once a human continues or exits the debugger in SAP GUI.
Set an external ABAP breakpoint on a specific line of a program, class method, or function module. Desktop backend only — WebGUI does not support external breakpoints.
Provide either line_number (1-indexed SAP display line) or match_pattern (substring or regex matched against source lines).
SAP toggles breakpoints: if the line already has a breakpoint, VKey 45 deletes it. This tool only sets the breakpoint — it does not run anything.
IMPORTANT — before calling this tool, ask the human operator for explicit permission and explain the consequences: there is NO tool to step, continue, or read variables in the resulting debugger. If the breakpoint later fires during a GUI run, SAP GUI opens a modal interactive ABAP debugger that only a human can drive — the agent cannot see or control it, and it may fire once per row/iteration if the code path repeats. The halted session is unusable for the agent until then, as described above. Only proceed once the human has confirmed they intend to sit at the SAP GUI and step through the debugger themselves; do not use this to silently 'verify a code path is reached' from an unattended flow.
Inputs: object_name (required), object_type (required), session, agent_id, +3 more. Returns: Result of sap_breakpoint_set.
sap_click_buttonSap Click ButtonA
Click a button on the current SAP screen by its label text.
Use sap_discover_buttons first to see available buttons. Prefer sap_press_key with keyboard shortcuts (F-keys, Ctrl+*) when available — they are faster and more reliable. Use this tool when no shortcut exists.
Args:
label: Button label text (e.g., 'Execute', 'Save', 'Ausführen')
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session
Inputs: label (required), session, agent_id. Returns: Result from sap_click_button tool.
sap_click_table_cellSap Click Table CellA
Click a cell in an ALV grid table. Automatically targets the correct clickable element (hotspot span vs TD). Use after sap_read_table to navigate to detail views.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: row (required), column (required), action, session, +1 more. Returns: Result from sap_click_table_cell tool.
sap_close_popupSap Close PopupA
Close an active popup dialog by clicking a button. Use when active_window shows 'wnd[1]' or higher and you want to dismiss the dialog. Note: Not all popups need closing - if the popup is a form you need to fill, use sap_discover_fields and sap_fill_form instead (they automatically target the active window). Specify button by label ('Ja', 'Nein') or accesskey ('J', 'N'), or use close=True to click the X button if available.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: close, button, session, agent_id. Returns: Result from sap_close_popup tool.
sap_discover_buttonsSap Discover ButtonsA
Discover clickable buttons on the current SAP screen. Returns buttons with label, selector/ID, shortcut (e.g. F3), and accesskey. Prefer keyboard shortcuts (sap_press_key) when available — they're faster and more reliable. To press a discovered button: use browser_click(selector) on WebGUI, or sap_com_evaluate(element_id, action='call', method='Press') on Desktop. For input fields use sap_discover_fields instead.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: session, agent_id. Returns: Result from sap_discover_buttons tool.
sap_discover_fieldsSap Discover FieldsA
Discover input fields on the current SAP screen (or active popup dialog). Returns fields with label, name, value, and a selector/ID for targeting the field. Automatically targets the active window — if a popup is open, shows popup fields. Use the label with sap_fill_form or sap_set_field to fill fields (works on both backends). The 'selector' field is a CSS selector on WebGUI or a SAP GUI element ID on Desktop. For buttons, use sap_discover_buttons instead.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: session, agent_id. Returns: Result from sap_discover_fields tool.
sap_fill_formSap Fill FormA
Fill multiple SAP form fields in a single call. Use this when filling 2+ fields on the SAME screen without UI navigation between them.
Keys can be:
Visible label text (e.g., 'First Name', 'Straße') — works on both backends
CSS selectors starting with '#' (WebGUI, e.g., '#M0:46:1:1::0:21')
SAP GUI element names (Desktop, e.g., 'BUT000-NAME_LAST')
When to use:
Filling a form with multiple input fields
All fields visible on current screen
No button clicks or navigation needed between fields
When NOT to use:
Single field only (use sap_set_field)
Fields on different screens/tabs
Need to click buttons between fills
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Example payload:
{"fields": {"Vorname": "Mario", "Nachname": "Rossi"}, "strict": false}
Inputs: fields (required), strict, session, agent_id. Returns: Result from sap_fill_form tool.
sap_get_capabilitiesSap Get CapabilitiesA
RECOMMENDED: Call at the start of every SAP session. Returns all available tools with their full descriptions. Reading this first helps you understand what capabilities are available, work faster, and avoid common mistakes like clicking buttons when keyboard shortcuts are available.
Inputs: no named parameters. Returns: Result from sap_get_capabilities tool.
sap_get_form_fieldsSap Get Form FieldsA
Discover fillable form fields on the current SAP screen (or active popup dialog). Returns field IDs, labels, types (text/dropdown/checkbox/radio), and current values. Automatically targets the active window — if a popup is open, shows popup fields. Use include_dropdown_options=True to also fetch available options for dropdown fields.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: session, agent_id, include_dropdown_options. Returns: Result from sap_get_form_fields tool.
sap_get_screen_infoSap Get Screen InfoB
Get technical information about the current SAP screen
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: session, agent_id. Returns: Result from sap_get_screen_info tool.
sap_get_screen_textSap Get Screen TextA
Get all readable text from the current SAP screen. Use include_dropdown_options=True to also fetch available options for dropdown fields.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: session, agent_id, include_dropdown_options. Returns: Result from sap_get_screen_text tool. Extracts all readable text from the curre…
sap_get_shortcutsSap Get ShortcutsA
Discover keyboard shortcuts available on the current SAP screen. Use BEFORE clicking buttons - shortcuts like F5, Ctrl+S are faster and more reliable. Returns action text and key combination for each available shortcut.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: session, agent_id. Returns: Result from sap_get_shortcuts tool.
sap_keepalive_startSap Keepalive StartB
Start a background task that keeps the SAP session alive
Inputs: session, agent_id, interval_seconds. Returns: Result from sap_keepalive_start/stop tools.
sap_keepalive_stopSap Keepalive StopC
Stop the background keepalive task
Inputs: session, agent_id. Returns: Result from sap_keepalive_start/stop tools.
sap_list_connectionsSap List ConnectionsA
List available SAP systems. Returns two sections: 'configured_systems' from systems.json (pass the 'key' field as system_key to sap_login), and 'connections' from SAP Logon (SAPUILandscape.xml, Desktop only). IMPORTANT: pass a configured_systems 'key' as system_key to sap_login, NOT a SAP Logon entry name. If configured_systems is empty, check config_error.
Inputs: no named parameters. Returns: Result from sap_list_connections tool.
sap_loginSap LoginA
Log into SAP. On WebGUI: requires Chrome with --remote-debugging-port=9222 and VPN (if internal SAP). On Desktop: opens a NEW parallel session each call — re-login does NOT replace prior logins. You can be logged into the same SAP Logon entry as multiple distinct (client, user) tuples concurrently. The returned LoginResult.session_id is the registry ID ('s1', 's2', ...) you pass on subsequent tool calls to address THIS specific login. Concurrency note: sessions on one connection share one single-threaded COM engine; parallel scripting loops on that connection run sequentially (no speedup). For bulk work on one connection, prefer one large loop in a single script. Parallelism helps only across separate connections/systems. Use sap_session_list to see all currently active sessions. Credentials are read from ~/.config/sap-mcp/systems.json. Use system_key (dictionary key from systems.json) to select a non-default system. Call sap_list_connections first to see available system keys.
Inputs: url, client, system_key. Returns: Result from sap_login tool.
sap_lookup_fieldsSap Lookup FieldsA
Look up known field CSS selectors for an SAP transaction (WebGUI only). Returns pre-discovered selectors from a static registry. On Desktop, use sap_discover_fields instead — it discovers fields dynamically.
Inputs: transaction (required). Returns: Result from sap_lookup_fields tool.
sap_press_keySap Press KeyA
Send a keyboard shortcut to SAP
Note on 'Escape': on the desktop backend it sends SAP VKey 12 (F12 / Cancel), not the Windows Esc key; its meaning is screen dependent (some editor screens open an 'Exit editor' dialog). On the WebGUI backend the key is passed to the browser as a normal key press (no VKey mapping). To dismiss a popup use sap_close_popup.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: key (required), session, agent_id. Returns: Result from sap_press_key tool. For shortcut keys (F-keys or Ctrl+*), the statu…
sap_quick_reportSap Quick ReportA
Execute a transaction, fill the selection screen (fields, checkboxes, radio buttons), press Execute (F8), and return the result — all in one call.
Works with any SAP report/list transaction that has a selection screen (VA05, ME2M, MB51, FBL1N, Z-transactions, etc.).
After execution, you remain on the result screen. If the result is 'unknown', use individual tools to investigate further.
If you already know a transaction shows a popup after F8 (e.g., a variant selection dialog), pass post_f8_keys=['Enter'] to dismiss it automatically.
Do NOT use for:
SE16 (use sap_se16_query instead)
SM37 (use sap_sm37_lookup instead — has job log support)
Transactions without selection screens (e.g., BP, VA01)
SE11/SE24/SE37 (use dedicated lookup tools)
WebGUI-only. Returns an error on desktop backend.
Inputs: tcode (required), fields, radios, session, +5 more. Returns: Result of sap_quick_report.
sap_read_se38_sourceRead SE38 SourceARead-onlyIdempotent
Read ABAP report source code from SE38. If sap-adt is available, prefer its get_source tool. Navigates to SE38, enters the program name, and displays the source code. Useful for verifying abapGit pull operations.
Inputs: program_name (required), session, agent_id. Returns: object
sap_read_status_barSap Read Status BarA
Read the current message from SAP's status bar
Also returns message_id / message_number (desktop only), which identify the message independently of the logon language, plus message_parameters (its &1-&4 runtime values, which may themselves be translated).
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: session, agent_id. Returns: Result from sap_read_status_bar tool.
sap_read_tableSap Read TableA
Read data from an ALV grid or table on the current screen
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: end_row, session, agent_id, max_rows, +1 more. Returns: Result from sap_read_table tool. For ALV grids, includes grid-level metadata wi…
sap_screenshotSap ScreenshotARead-only
Take a screenshot of the current SAP screen.
Returns a PNG screenshot as an image. Works on both WebGUI and Desktop backends. ⚠️ Screenshots consume significant context tokens. Prefer sap_get_screen_text or sap_get_form_fields for reading screen content. Use screenshots only for visual debugging or when the user explicitly requests one.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session
Inputs: session, agent_id.
sap_se09_lookupSap Se09 LookupARead-only
Look up transport requests from SE09 (Transport Organizer). If sap-adt is available, prefer its get_transport_requests for listing transports. USE THIS for transport release on ECC (ADT release silently fails on ECC) or when ADT is unavailable. Returns transport requests with owner, description, status, type, and target system. By default shows only modifiable requests for the current user. Supports filtering by username, request type (workbench/customizing), and status (modifiable/released/all).
Inputs: status, session, agent_id, username, +3 more. Returns: Result of SE09 transport lookup.
sap_se11_lookupSap Se11 LookupARead-only
Look up table or structure metadata from SE11 (ABAP Dictionary). If sap-adt is available, prefer its get_table_fields or get_object_info tools. USE THIS instead of sap_transaction('SE11') - faster and returns structured data. Returns field names, data types, lengths, and descriptions. Supports single name or list of names. Always queries live from SAP. Use object_type='table' for database tables, 'structure' for data structures. For large requests (>10 objects), provide output_file to write results to JSON file instead of returning inline (avoids context overflow).
Inputs: names (required), object_type (required), session, agent_id, +1 more. Returns: result
sap_se16_querySap Se16 QueryARead-only
Query SAP table data via SE16N (Data Browser). If sap-adt is available, prefer its run_query tool for simple queries. USE THIS for complex queries with dynamic filtering or when ADT is unavailable.
Filters: If a filter cannot be applied (e.g. the field is unknown or not offered by SE16N), the call fails before running the query; the error lists the SE16N selection fields when they could be read. On the WebGUI backend a filter goes into the row whose technical name matches, and only the first ~30 rows of the selection grid are rendered, so a field further down a wide table cannot be filtered (the error says so).
Performance: ~7 rows/second due to pagination.
100 rows: ~14 seconds
500 rows: ~1.5 minutes
1000 rows: ~2.5 minutes
5000 rows: ~12 minutes
For large results, use output_file to write JSON to disk and receive a summary.
Inputs: table (required), filters, session, agent_id, +2 more. Returns: result
sap_se24_editSap Se24 EditADestructive
Edit an existing class method in SE24 (Class Builder). If sap-adt is available, prefer its patch_source or set_source_from_file tools — faster, no GUI needed.
Replaces the method's source code, runs syntax check (Ctrl+F2), and activates (Ctrl+F3). Auto-reverts if check or activation fails.
Important: Only for EXISTING classes and methods. To create new ones, use abapGit.
Workflow: Read current class with sap_se24_lookup first to see methods, then call this tool with the full new method source.
Inputs: class_name (required), new_source (required), method_name (required), session, +1 more. Returns: Result of editing a class method in SE24.
sap_se24_lookupSap Se24 LookupARead-only
Look up class/interface metadata from SE24 (Class Builder). If sap-adt is available, prefer its get_source/get_class_definition tools. USE THIS instead of sap_transaction('SE24') - faster and returns structured data. Returns class structure including methods with parameters, attributes, and implemented interfaces. Supports single class or list of classes. Each method includes: name, visibility, parameters, exceptions, and description.
Inputs: classes (required), session, agent_id, output_file. Returns: result
sap_se37_editSap Se37 EditADestructive
Edit an existing ABAP function module in SE37. If sap-adt is available, prefer its patch_source or set_source_from_file tools — faster, no GUI needed.
Replaces the entire source code, runs syntax check (Ctrl+F2), and activates (Ctrl+F3). Auto-reverts if check or activation fails.
Important: Only for EXISTING function modules. To create new ones, use abapGit.
Workflow: Read current source with sap_se37_lookup first (check the Quelltext/Source Code tab), modify it, then call this tool with the full new source.
Inputs: new_source (required), function_module (required), session, agent_id. Returns: Result of editing a function module in SE37.
sap_se37_lookupSap Se37 LookupARead-only
Look up function module metadata from SE37 (Function Builder). If sap-adt is available, prefer its get_source tool for reading FM source code. USE THIS instead of sap_transaction('SE37') - faster and returns structured data. Returns function module signature including import/export/changing/tables parameters and exceptions. Supports single FM or list of FMs. Each parameter includes: name, typing (LIKE/TYPE), reference type, default value, optional flag, and description.
Inputs: function_modules (required), session, agent_id, output_file. Returns: result
sap_se38_editSap Se38 EditADestructive
Edit an existing ABAP report in SE38. If sap-adt is available, prefer its patch_source or set_source_from_file tools — faster, no GUI needed.
Replaces the entire source code, runs syntax check (Ctrl+F2), and activates (Ctrl+F3). Auto-reverts if check or activation fails.
Important: Only for EXISTING reports. To create new reports, use abapGit.
Workflow: Read current source with sap_read_se38_source first, modify it, then call this tool with the full new source.
Inputs: new_source (required), program_name (required), session, agent_id. Returns: Result of editing an ABAP report in SE38.
sap_se93_lookupSap Se93 LookupARead-only
Look up transaction metadata from SE93 (Transaction Maintenance). USE THIS instead of sap_transaction('SE93') - faster and returns structured data. Returns transaction description, program, screen/selection info, and GUI capabilities. Supports single tcode or list of tcodes. Currently supports 'dialog' and 'report' transaction types.
Inputs: tcodes (required), session, agent_id, output_file. Returns: result
sap_select_dropdownSap Select DropdownA
Select a value from a dropdown (combobox) field on the current SAP screen.
Use sap_get_form_fields(include_dropdown_options=True) first to see available dropdown fields and their options.
Unlike sap_set_field which auto-detects field type, this tool is specifically for dropdown selection and returns available_options on failure.
Args:
label: Dropdown field label text (e.g., 'Country', 'Language', 'Buchungskreis')
value: Exact option text to select from the dropdown
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session
Inputs: label (required), value (required), session, agent_id. Returns: Result from sap_select_dropdown tool.
sap_select_tabSap Select TabA
Select a tab on the current SAP screen by its label text.
Use sap_get_screen_text to see available tab labels on the current screen.
Args:
label: Tab label text (e.g., 'Address', 'Details', 'Allgemeine Daten')
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session
Inputs: label (required), session, agent_id. Returns: Result from sap_select_tab tool.
sap_session_bindSap Session BindA
Claim exclusive ownership of a SAP session for the calling agent. Strict by default (#643): if the session is already bound to a different agent, the call fails — pick a different session via sap_session_list, or retry with force=true to take over (use only for crash recovery, otherwise prefer leaving the existing binding intact). Re-binding the same agent is a no-op success.
Inputs: agent_id (required), session_id (required), force. Returns: Result from sap_session_bind tool.
sap_session_closeSap Session CloseA
Close a SAP session.
Closes the underlying SAP GUI session/tab and removes it from the registry. Any session ID can be closed, including "s1". With the parallel-multi-mandant contract (#671), the registry can hold multiple concurrent logins and you may legitimately want to close any of them — including the lowest-numbered one. If you close the only remaining session, the next tool call will fail with a clear "no session" error and you should call sap_login() again.
Sessions with origin "attached" (a window the user already had open) are never closed by this server: the call is refused and points at sap_session_detach.
Args: session_id: Session to close (e.g. "s1", "s2", ...)
Inputs: session_id (required). Returns: Result from sap_session_close tool.
sap_session_detachSap Session DetachA
Stop using a session WITHOUT closing it (desktop backend only).
Removes the session from the registry, drops its agent binding and stops watching its connection. No SAP GUI call is made: the SAP window stays open. This is the only way to drop an "attached" session (a window the user already had open, which sap_session_close refuses to close); it also works on sessions this server opened. The WebGUI backend has no detach; use sap_session_close there.
Args: session_id: Session to detach (e.g. "s2")
Inputs: session_id (required). Returns: Result from sap_session_detach tool.
sap_session_listSap Session ListA
List all active SAP sessions.
Returns session IDs, current transaction, screen title, client, user, and system_name for each. Use this to see what sessions exist before targeting one.
The first sap_login() registers "s1". Additional sessions come from:
repeated sap_login() calls (parallel multi-mandant — each new login adds a session alongside the existing ones, not replacing them — see #671)
sap_transaction(tcode, new_window=True) (a /o sub-session of an existing connection, sharing its login)
Desktop: when another call has been running on the connection's single COM
engine for a while, the result carries a com_engine block saying which
connection is busy and since when. That running call is why other tool calls
on the same connection hang — wait for it instead of retrying.
Inputs: no named parameters. Returns: Result from sap_session_list tool.
sap_session_releaseSap Session ReleaseA
Release agent binding from a session. Use when an agent finishes work and wants to free the session for other agents or general use.
Inputs: session_id (required). Returns: Result from sap_session_release tool.
sap_session_reset_to_primarySap Session Reset To PrimaryA
Bulk-close every SAP session except the primary one (s1). Use this when parallel agents have left orphaned/extra windows and you want to return to a known-clean state with only s1 open. Reconciles the registry first (drops any sessions that died externally), then closes the rest. WARNING: if you call this from a non-primary session, your own session will be closed and you will appear in killed_agents — your next tool call will fail until you rebind to s1 (or another surviving session) via sap_session_bind. See issue #637 for the parallel-agent drift scenario this addresses.
Inputs: no named parameters. Returns: Result from sap_session_reset_to_primary tool. Reports the outcome of bulk-clos…
sap_session_statusSap Session StatusC
Check the current SAP session status
Inputs: session, agent_id. Returns: Result from sap_session_status tool.
sap_set_checkboxSap Set CheckboxA
Set a SAP checkbox to checked or unchecked by its label text.
Use sap_get_form_fields first to see available checkboxes and their current state.
Args:
label: Checkbox label text (e.g., 'Workbench-Aufträge', 'Freigegeben')
checked: True to check, False to uncheck
Only label lookup is supported. If the label is ambiguous or not found: on the desktop backend use sap_com_evaluate or sap_run_script and set .selected = True/False on the element by id (both are desktop-only); on the WebGUI backend use browser_evaluate.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session
Inputs: label (required), checked (required), session, agent_id. Returns: Result from sap_set_field tool.
sap_set_fieldSap Set FieldA
Set a single SAP form field by label, CSS selector, or element name. Finds the field dynamically and fills it with the given value.
The label parameter can be:
Visible label text (e.g., 'Last Name', 'Nachname') — works on both backends
CSS selector (WebGUI, e.g., '#M0:46:1:1::0:21')
SAP GUI element name (Desktop, e.g., 'BUT000-NAME_LAST')
This is simpler than sap_fill_form for single fields.
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session (for parallel agents)
Inputs: label (required), value (required), session, agent_id. Returns: Result from sap_set_field tool.
sap_set_radio_buttonSap Set Radio ButtonA
Select a SAP radio button by its label text.
Use sap_get_form_fields first to see available radio buttons and which is selected.
Args:
label: Radio button label text (e.g., 'Datenbanktabelle', 'Database table')
Session parameter:
session=None (default): Uses primary session ("s1")
session="s2": Targets specific session
Inputs: label (required), session, agent_id. Returns: Result from sap_set_field tool.
sap_slg1_lookupSap Slg1 LookupARead-only
Search and read SAP application logs from SLG1. USE THIS instead of sap_transaction('SLG1') - faster and returns structured data. Returns log entries with metadata (date, time, user, object, subobject, external ID, message count, log number). Best used when the log object is known (e.g., /SDF/CALM for Cloud ALM, /SDF/AIMAX for AI). Use '*' as object to search all logs. Requires at minimum the 'object' parameter. Returns up to 50 logs.
Inputs: object (required), session, to_date, agent_id, +4 more. Returns: result
sap_sm30_lookupSap Sm30 LookupARead-only
Look up SAP table maintenance view entries from SM30 (read-only display mode). USE THIS instead of sap_transaction('SM30') - faster and returns structured data. Returns entries from the maintenance view with dynamically-parsed columns. Supports any flat table view (e.g., V_T005 for countries, custom Z* views). Non-flat views (SM34/cluster/hierarchical) are detected and reported as unsupported. Note: only the first page of rows is returned (typically ~12 rows); views with more entries will report the total row_count from the view header.
Inputs: view_name (required), session, agent_id, output_file. Returns: result
sap_sm37_lookupSap Sm37 LookupARead-only
List background jobs from SM37 (Job Overview). USE THIS instead of sap_transaction('SM37') - faster and returns structured data.
Filters: job name (wildcards like BILLING), username, status (scheduled/released/ready/active/finished/canceled), date range.
Note: status=None keeps SAP defaults (all checked except 'Scheduled'). Pass status=['scheduled'] explicitly to include only scheduled jobs.
When include_log=True and exactly one job matches, the job log is included.
Returns job list with name, status, start time, duration, user, and SAP client (mandant).
Inputs: status, session, to_date, agent_id, +5 more. Returns: Result of SM37 job list lookup.
sap_spro_searchSap Spro SearchARead-only
Search the SAP Implementation Guide (IMG) for customizing activities by keyword. USE THIS to find where specific SAP configuration is maintained (e.g., 'country', 'pricing', 'tax'). Returns matching IMG activities with their parent node and area. The WebGUI search covers all IMG text content; the desktop search only the top two levels of the IMG tree (the result's scope_note says so). Results can then be used to navigate to specific configuration via SM30 or other transactions.
Note: First search in a language may be slow (30-60s) while the text index is built. Subsequent searches are faster.
Inputs: query (required), session, agent_id, output_file. Returns: result
sap_st22_lookupSap St22 LookupARead-only
Look up ABAP short dumps (runtime errors) from ST22. If sap-adt is available, prefer its list_short_dumps/get_short_dump_details tools. USE THIS instead of sap_transaction('ST22') - faster and returns structured data. Two-step workflow: call once without dump_index to list dumps, then call again with dump_index=N to read a specific dump's detail. By default lists today's dumps. Use date parameter for other dates.
Inputs: date, session, agent_id, dump_index, +1 more. Returns: result
sap_transactionSap TransactionA
Enter and execute an SAP transaction code. IMPORTANT: Do NOT use this for SE11, SE16, SE24, SE37, or SE93; use sap_se11_lookup, sap_se16_query, sap_se24_lookup, sap_se37_lookup, or sap_se93_lookup.
Multi-Session Support (for parallel agents): new_window=True opens a new SAP session and returns session_id/session_count; pass session on later calls to target it.
Concurrency note: SAP GUI COM scripting is single-threaded per connection. Running parallel scripting loops across new_window=True sessions of the same connection is serialized (no speedup). For bulk work on one connection, use one script with a larger loop; parallelize only across separate connections.
⚠️ CRITICAL: Always close sessions you opened! Close new_window=True sessions with sap_session_close to avoid hitting SAP session limits. Use sap_session_list to review open IDs.
Inputs: tcode (required), session, agent_id, new_window, +1 more. Returns: Result from sap_transaction tool.
search_classesSearch ClassesARead-only
Search for SAP classes by name or description. Use this when the user asks things like:
'What class handles installations?'
'Find classes for IS-U contracts'
'Which class works with devices?'
'Show me FI-CA classes'
The catalog contains IS-U and FI-CA classes. Returns matching classes with relevance scores.
Inputs: query (required), limit. Returns: Response from class search.
search_function_modulesSearch Function ModulesARead-only
Search for SAP function modules by name, description, or parameter. Use this when the user asks things like:
'What FM reads installation data?'
'Find function modules for Anlage'
'Which FMs work with business partners?'
'Show me FKK function modules'
The catalog contains IS-U and FI-CA function modules. Returns matching FMs with relevance scores.
Inputs: query (required), limit, include_params. Returns: Response from function module search.
search_tablesSearch TablesARead-only
Search for SAP tables by name, description, or field. Use this when the user asks things like:
'What table stores material master data?'
'Which table has the MATNR field?'
'Find tables related to purchase orders'
Returns matching tables with relevance scores.
Inputs: query (required), limit, include_fields. Returns: Response from table search.
search_transactionsSearch TransactionsARead-only
Search for SAP transactions by description or transaction code. Use this when the user asks things like:
'How do I create a sales order?'
'What transaction displays customer master?'
'Show me material management transactions'
'What is VA01?'
Returns matching transactions with relevance scores.
Inputs: query (required), area, limit. Returns: Response from transaction search. NOTE: `success` is always True because this t…
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 71 tools
Many tools are transaction- or object-specific, but the set contains clear overlaps: sap_get_form_fields vs sap_discover_fields, sap_set_field vs sap_select_dropdown/sap_fill_form, sap_screenshot vs browser_screenshot, and browser_* UI controls vs the SAP-native click/fill/keyboard tools. Descriptions give preferred-order hints, but boundaries remain fuzzy enough that an agent can easily choose the wrong discovery or interaction tool.
All names use lower_snake_case, but there is no uniform verb_noun pattern: sap_get_screen_text and sap_set_field coexist with sap_transaction, sap_session_list, sap_keepalive_start, and sap_abapgit_list_repos. The sap_*, browser_*, search_*, log_*, and bare choose prefixes namespace some tools, but verb order and prefix conventions are mixed.
At 71 tools this surface is extremely oversized for a single MCP server, even for the broad SAP GUI automation domain. It includes overlapping UI layers, auxiliary logging/choice tools, and multiple session-management utilities that would be better consolidated or split into focused servers.
Coverage is unusually broad: login/session management, screen/form interaction, transactions, table/query lookups, ABAP metadata and editing, transports, logs, jobs, dumps, IMG search, and abapGit. Gaps remain around ABAP debugger control and creating new ABAP objects, but those are explicitly scoped limitations rather than fatal omissions.
Maintenance
Related MCP Connectors
Connect your agents to any website. The cheaper, faster and more reliable alternative to browser use
Eyes and hands on real Windows PCs — observe, click, type via Glasswarp API.
Let your AI agent operate any website through a real, logged-in browser session.
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
Related MCP Servers
- AlicenseBqualityCmaintenanceAutomates interactions with SAP GUI using the Model Context Protocol, allowing precise control of SAP transactions through tools like clicking, typing, scrolling, and transaction management.12147MIT
- AlicenseNot gradedqualityCmaintenanceEnables MCP-compatible AI platforms to see the screen and operate any desktop software through real mouse clicks, text input, key presses, and scripted scenario execution.MIT
- AlicenseAqualityBmaintenanceEnables AI agents to execute SAP tasks through a cost-routing MCP server that tries API, recorded scripts, WebGUI, and computer-use vision in cheapest-first order, falling back only when needed. It can also promote an interactive GUI routine into a reusable recorded script to make repeat runs nearly free.1MIT
- AlicenseAqualityBmaintenanceEnables AI tools to operate IBM i 5250 green screens, driving and testing interactive RPG programs by seeing screens, typing into fields, and pressing keys.626 npm1Apache 2.0