Oracle H

io.github.tponscr-debugPublished by GitHub account tponscr-debugv1.0.0Updated Oct 24, 2026

Human approval gate for AI agents. Critical actions approved or rejected by a human via Telegram.

Overview

AI-generated overview

Lets an assistant route critical actions to a human for approval or rejection through Telegram before proceeding.

What you can do
Oracle H acts as a human approval gate for AI agents. According to its description, critical actions are approved or rejected by a human via Telegram, so an agent can pause and wait for a person's decision instead of acting unilaterally. The manifest lists no tools, so the exact callable operations are not documented here.
When to use it
Consider it when an agent performs consequential actions and you want a person to confirm or deny them before they happen. It fits workflows where a Telegram-based approval step is an acceptable checkpoint.
Requirements
Runs locally as a stdio process, started with npx from the npm package oracle-h-mcp; desktop only. Requires the environment variable ORACLE_BASE_URL (defaults to the ORACLE-H service base URL) and the required secret ORACLE_SIGNATURE_KEY for authentication. Network access to the ORACLE-H service is implied.
Before you install
The required secret ORACLE_SIGNATURE_KEY is used for authentication; the manifest notes a demo value for testing without signup, which should not be used in production. Approval decisions depend on the external ORACLE-H service and Telegram, so action details may leave your machine. No tools are listed, so review what the server actually sends before relying on it.

Installation

In SourceWeft

  1. Open Oracle H in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

This repository has no README.

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

25% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.