Kasbah MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 55 installs a week from npm. Last commit 21 Feb 2026.
Governance layer for agentic AI — signed, verifiable receipts for every agent action.
We read the source, 21 h ago · rules 3dff92dd89df
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
subprocess.check_call([py_exe, "-m", "pip", "install", "numpy"])
p = subprocess.run(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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 kasbah-mcp -- npx -y @yobekasbah/mcp-server
{
"mcpServers": {
"kasbah-mcp": {
"args": [
"-y",
"@yobekasbah/mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.kasbah-mcp]
command = "npx"
args = ["-y", "@yobekasbah/mcp-server"]
{
"mcpServers": {
"kasbah-mcp": {
"args": [
"-y",
"@yobekasbah/mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"kasbah-mcp": {
"args": [
"-y",
"@yobekasbah/mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
KASBAH_API_KEY (Kasbah API key — get a free one via POST https://kasbah-api.fly.dev/v1/auth/signup), KASBAH_API (Kasbah gateway base URL (defaults to http://127.0.0.1:8788 for local dev)).
The author declared them in the registry entry; get the values from the project itself.
Ed25519-signed receipts for every AI agent action. Local-first, verifiable, no server required.
Signed, hash-chained provenance receipts for AI agent actions.
Verifiable agent memory with signed ledger receipts — verify every write offline.
Verifiable action logs for AI agents. Every action is recorded in a SHA-256 hash chain.
Tamper-proof audit trail for AI agents. Signed receipts, offline-verifiable, zero backend.
Independent effect verification and signed receipts for consequential AI agent actions.
Signed deterministic AI-governance measurement: EU AI Act cards + agent-callable record verify.
Governed AI actions with signed, verifiable receipts: free keyless reads, human-approved writes.
Answers built from our own checks of this server.