Sap Adt MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 158 installs a week from npm. Last commit 9 Oct 2026.
Give Claude live access to SAP ABAP via ADT: read, search, check, test, and edit objects.
We read the source, 2 d ago · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
return { ok: true, content: fs.readFileSync(p, "utf8") };
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
этот файл ставится пользователю, но в репозитории его нет
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add sap-adt-mcp -- npx -y sap-adt-mcp
{
"mcpServers": {
"sap-adt-mcp": {
"command": "npx",
"args": [
"-y",
"sap-adt-mcp"
]
}
}
}
[mcp_servers.sap-adt-mcp]
command = "npx"
args = ["-y", "sap-adt-mcp"]
{
"mcpServers": {
"sap-adt-mcp": {
"command": "npx",
"args": [
"-y",
"sap-adt-mcp"
]
}
}
}
{
"servers": {
"sap-adt-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"sap-adt-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
SAP_ADT_MCP_CONFIG (Absolute path to your config.json (host/client/user/password per SAP system). Defaults to ~/.sap-adt-mcp/config.json. See config.example.json in the repo).
robots.txt tester (RFC 9309), AI crawler access (GPTBot, ClaudeBot...) and sitemap check.
SEO check of any website and AI crawler access test (access pass), and the full Audit.
Free live-app check by an AI agent. On request it fixes the code and tests the app again.
Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
Search, price and buy field-tested agent-ops kits (evals, security, runbooks) via Stripe checkout.
Check, test, prove and review a rowstile policy: access rules for Postgres row-level security
Read-only tools that check whether code, and the tests that claim it works, are real.
Answers built from our own checks of this server.