Oracle H runs on your own machine — the client starts it, so there is no endpoint to ping. 45 installs a week from npm.
Human approval gate for AI agents. Critical actions approved or rejected by a human via Telegram.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
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 oracle-h -e 'ORACLE_SIGNATURE_KEY=<ORACLE_SIGNATURE_KEY>' -- npx -y oracle-h-mcp
{
"mcpServers": {
"oracle-h": {
"command": "npx",
"args": [
"-y",
"oracle-h-mcp"
],
"env": {
"ORACLE_SIGNATURE_KEY": "<ORACLE_SIGNATURE_KEY>"
}
}
}
}
[mcp_servers.oracle-h]
command = "npx"
args = ["-y", "oracle-h-mcp"]
env = { ORACLE_SIGNATURE_KEY = "<ORACLE_SIGNATURE_KEY>" }
{
"mcpServers": {
"oracle-h": {
"command": "npx",
"args": [
"-y",
"oracle-h-mcp"
],
"env": {
"ORACLE_SIGNATURE_KEY": "<ORACLE_SIGNATURE_KEY>"
}
}
}
}
{
"servers": {
"oracle-h": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"oracle-h-mcp"
],
"env": {
"ORACLE_SIGNATURE_KEY": "<ORACLE_SIGNATURE_KEY>"
}
}
}
}
Put your own value in place of
<ORACLE_SIGNATURE_KEY> (Your ORACLE-H signature key for authentication. Use 'demo-signature-key-change-in-production' for testing with no signup required).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
ORACLE_BASE_URL (ORACLE-H service base URL. Defaults to https://oracle-h.online).
Gate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.
Human-in-the-loop for AI coding agents — ask questions, get approvals via Slack.
A real email inbox for AI agents: human-approved sends, untrusted-by-default inbound.
Governed email for AI agents: a sandbox inbox to read and send from, human approval to go external.
Email inboxes for AI agents: send, reply, read verification codes, human-approved drafts.
Shared AI memory for teams: a git vault of markdown, human-approved, injection-safe, local-only.
WhatsApp and Telegram for AI agents, behind a policy gateway. OAuth or access key.
Full Telegram Bot control for AI agents via pure Bot API: zero login risk, one Bot Token.
Answers built from our own checks of this server.