Consentgate MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 31 installs a week from npm. Last commit 4 Jun 2026.
Gate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.
Nothing serious here today
Today is the operative word: we check Consentgate MCP 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 consentgate-mcp -e 'CONSENTGATE_API_KEY=<CONSENTGATE_API_KEY>' -- npx -y consentgate-mcp{
"mcpServers": {
"consentgate-mcp": {
"command": "npx",
"args": [
"-y",
"consentgate-mcp"
],
"env": {
"CONSENTGATE_API_KEY": "<CONSENTGATE_API_KEY>"
}
}
}
}[mcp_servers.consentgate-mcp]
command = "npx"
args = ["-y", "consentgate-mcp"]
env = { CONSENTGATE_API_KEY = "<CONSENTGATE_API_KEY>" }{
"mcpServers": {
"consentgate-mcp": {
"command": "npx",
"args": [
"-y",
"consentgate-mcp"
],
"env": {
"CONSENTGATE_API_KEY": "<CONSENTGATE_API_KEY>"
}
}
}
}{
"servers": {
"consentgate-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"consentgate-mcp"
],
"env": {
"CONSENTGATE_API_KEY": "<CONSENTGATE_API_KEY>"
}
}
}
}Put your own value in place of
<CONSENTGATE_API_KEY> (ConsentGate API key (cg_…) from https://consentgate.fyi/dashboard/keys).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
CONSENTGATE_BASE_URL (Override the API base URL (defaults to https://consentgate.fyi)).
Alternatives to Consentgate MCP
same job, measured the same wayHuman approval gate for AI agents. Critical actions approved or rejected by a human via Telegram.
Human-in-the-loop for AI coding agents — ask questions, get approvals via Slack.
Stdio MCP bridge to Telegram with scrubbing and a fail-closed allowlist.
Give your agent its own email address with graduated human oversight, from approval to autonomy.
Central Slack/Telegram router with jobs, memory, approvals, and A2A delegation
Every email and calendar account you connect, for AI agents, with permissions and approvals.
Governed email for AI agents: a sandbox inbox to read and send from, human approval to go external.
Read a personal Telegram account over MTProto; every write is a plan a human applies.
Consentgate MCP — questions
Answers built from our own checks of this server.