Delego runs on your own machine — the client starts it, so there is no endpoint to ping. 202 installs a week from pypi. Last commit 11 Jun 2026.
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
Today is the operative word: we check Delego 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 delego -- uvx delego
{
"mcpServers": {
"delego": {
"args": [
"delego"
],
"command": "uvx"
}
}
}
[mcp_servers.delego]
command = "uvx"
args = ["delego"]
{
"mcpServers": {
"delego": {
"args": [
"delego"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"delego": {
"args": [
"delego"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
DELEGO_HOME (Directory holding the policy, signing keys, and audit ledger (defaults to ~/.delego). Set this to keep state project-scoped, e.g. /abs/path/to/project/.claude/.delego.).
The author declared them in the registry entry; get the values from the project itself.
Human-in-the-loop review and approval for AI agents. Audit trail, approval policies, native MCP.
Let AI agents query and operate business systems with authorization, approval and audit trails.
Governance proxy for MCP servers — policy evaluation, human approval, audit trails.
Supervised API-write gateway for AI agents with policy, human approval and execution receipts.
Gate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.
MCP adapter for Agent_Sudo: authorization, delegation, provenance, and audit for AI agents.
Human-in-the-loop approval for agent actions, with verifiable action-bound receipts.
Identity, authorization, audit trails, and revocable permissions for AI agents accessing MCP tools.
Answers built from our own checks of this server.