MCP server

Oracle H

io.github.tponscr-debug/oracle-h

Checked 26 Oct 2026, 08:31 UTC · Still published on its registry; checked against OSV.dev; never run by us

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

Runs on your computer

Source

At a glance

Type: MCP server
Publisher: Not verified
Status: Runs on your computer
Sets up in: Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code
Last checked: 26 Oct 2026, 08:31 UTC

Connect it to your agent

Add to Cursor Add to VS Code VS Code Insiders

Opens the app, which shows the server and asks you to confirm. It then runs the package on your computer with your permissions. For other apps, copy the setup below.

Claude Code

claude mcp add oracle-h --env ORACLE_SIGNATURE_KEY=YOUR_VALUE -- npx -y oracle-h-mcp@1.0.0

Claude Desktop

{"mcpServers":{"oracle-h":{"command":"npx","args":["-y","oracle-h-mcp@1.0.0"],"env":{"ORACLE_SIGNATURE_KEY":"YOUR_VALUE"}}}}

Codex (config.toml)

[mcp_servers.oracle-h]
command = "npx"
args = ["-y","oracle-h-mcp@1.0.0"]
env = { ORACLE_SIGNATURE_KEY = "YOUR_VALUE" }

Gemini CLI

{"mcpServers":{"oracle-h":{"command":"npx","args":["-y","oracle-h-mcp@1.0.0"],"env":{"ORACLE_SIGNATURE_KEY":"YOUR_VALUE"}}}}

Cursor

{"mcpServers":{"oracle-h":{"command":"npx","args":["-y","oracle-h-mcp@1.0.0"],"env":{"ORACLE_SIGNATURE_KEY":"YOUR_VALUE"}}}}

VS Code

{"servers":{"oracle-h":{"type":"stdio","command":"npx","args":["-y","oracle-h-mcp@1.0.0"],"env":{"ORACLE_SIGNATURE_KEY":"YOUR_VALUE"}}}}

Runs on your computer with your permissions: check the package and its source before installing. Replace YOUR_VALUE with your own ORACLE_SIGNATURE_KEY.

Browse

Related MCP servers

Agent Control — Action Gate
Agent asks a person go/stop/wait before Slack, CRM or risky steps. $49 for 30 days.
Approval Rules
Auto-approve small agent actions under your rules; approval cards for the rest.
AppGoat
App Store and Google Play data: apps, reviews, keywords, charts, competitors, ASO playbooks.
OAIA Arena
Score AI trading agents against 2,048 coin-flipping monkeys. Public leaderboard.
Overwing
Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.
Glyt
Human-in-the-loop approval for agent actions, with verifiable action-bound receipts.
Taste
Expert review for AI agents. On-chain proof of human review.
Invoice Preflight
Evidence-backed UBL, PDF, and image invoice checks before approval or payment.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.tponscr-debug/oracle-h.svg)](https://aptlynx.net/servers/io.github.tponscr-debug/oracle-h)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents