Almega runs on your own machine — the client starts it, so there is no endpoint to ping. 87 installs a week from pypi.
The immutable delegation frame for AI agents: gate any sensitive action, human-in-the-loop.
Today is the operative word: we check Almega every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 almega-mcp -- uvx almega-mcp
{
"mcpServers": {
"almega-mcp": {
"command": "uvx",
"args": [
"almega-mcp"
]
}
}
}
[mcp_servers.almega-mcp]
command = "uvx"
args = ["almega-mcp"]
{
"mcpServers": {
"almega-mcp": {
"command": "uvx",
"args": [
"almega-mcp"
]
}
}
}
{
"servers": {
"almega-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"almega-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
ALMEGA_BACKEND (Storage backend: 'memory' (default, zero-config) or 'stripe' (real Stripe Issuing test-mode virtual cards, no real money)), STRIPE_SECRET_KEY (Stripe TEST secret key (sk_test_...). Required only when ALMEGA_BACKEND=stripe. Almega refuses live keys).
VantaGate MCP Server & OpenAPI integration - Human-in-the-Loop for AI Agents
Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve.
Human-in-the-loop for AI agents. Submit choices, get a human decision.
Impri MCP server — human-in-the-loop approval inbox for AI agents
WhatsApp MCP Server - Human-in-the-loop for AI agents via WhatsApp
Human-in-the-loop approval for agent actions, with verifiable action-bound receipts.
Human in the loop for AI agents: ask ID verified people to check a decision before acting.
AI-native browser runtime for autonomous agents with human-in-the-loop supervision
Answers built from our own checks of this server.