Logi Approval runs on your own machine — the client starts it, so there is no endpoint to ping. 24 installs a week from npm. Last commit 7 Aug 2026.
logi Agent Approval Gate — human approval on the phone before high-risk agent actions.
Nothing serious here today
Today is the operative word: we check Logi Approval every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
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 logi-approval -- npx -y @logi-auth/mcp-approval{
"mcpServers": {
"logi-approval": {
"args": [
"-y",
"@logi-auth/mcp-approval"
],
"command": "npx"
}
}
}[mcp_servers.logi-approval]
command = "npx"
args = ["-y", "@logi-auth/mcp-approval"]{
"mcpServers": {
"logi-approval": {
"args": [
"-y",
"@logi-auth/mcp-approval"
],
"command": "npx"
}
}
}{
"mcpServers": {
"logi-approval": {
"args": [
"-y",
"@logi-auth/mcp-approval"
],
"command": "npx"
}
}
}This one needs environment variables set before it will start:
LOGI_AGENT_TOKEN (Bearer token issued at agent registration (start.1pass.dev developer console).), LOGI_AGENT_PUBLIC_ID (Public agent id (agt_...).), LOGI_AGENT_PRIVATE_KEY (Ed25519 private key PEM for signed mode (recommended).), LOGI_API_URL (logi API base URL. Defaults to https://api.1pass.dev.).
The author declared them in the registry entry; get the values from the project itself.
Alternatives to Logi Approval
same job, measured the same wayAsk a human before your agent acts: approval requests decided on a phone.
Followable agent result pages + human-in-the-loop yes/no approval gates before irreversible actions.
Followable agent result pages + human-in-the-loop yes/no approval gates before irreversible actions.
Human-in-the-loop approval for agent actions, with verifiable action-bound receipts.
Human approval gate for AI agents. Critical actions approved or rejected by a human via Telegram.
Fail-closed human approval gates for AI agent actions. Default-deny, TTL expiry, audit log.
Gate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.
Gate an AI agent's destructive actions behind human approval, with a tamper-evident log.
Logi Approval — questions
Answers built from our own checks of this server.