Actenon Kernel runs on your own machine — the client starts it, so there is no endpoint to ping. 350 installs a week from pypi. Last commit 3 Nov 2026.
Verify consequential AI actions before they execute.
We read the source, 5 d ago · rules 995398eba69f
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.
d := filepath.Join(corpus, c.ID)
p = subprocess.run([mcp, "--demo"], input=b"", capture_output=True, timeout=20)
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 kernel -- uvx actenon-kernel
{
"mcpServers": {
"kernel": {
"command": "uvx",
"args": [
"actenon-kernel"
]
}
}
}
[mcp_servers.kernel]
command = "uvx"
args = ["actenon-kernel"]
{
"mcpServers": {
"kernel": {
"command": "uvx",
"args": [
"actenon-kernel"
]
}
}
}
{
"servers": {
"kernel": {
"type": "stdio",
"command": "uvx",
"args": [
"actenon-kernel"
]
}
}
}
Authorize consequential AI agent actions before execution
MUJ428 verifies intent and evidence before consequential AI-agent actions.
AI Agent Firewall. Enforce signed authority before consequential actions. Free API key required.
Independent effect verification and signed receipts for consequential AI agent actions.
Pre-execution governance for AI agents. Validates tool calls before they execute.
Pre-action gate: verify before pay/trade/write/deploy. execute=true only on ALLOW.
Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
Private, voluntary AI-assisted conciliation with human approval before consequential actions.
Answers built from our own checks of this server.