Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by tponscr-debug • Uncategorized
A safety infrastructure MCP server that requires human approval via Telegram before autonomous AI agents execute critical or destructive actions.
Ensure human approval before executing destructive actions like deleting files or dropping databases.
Validate external write operations such as sending emails or posting to APIs.
Secure financial or infrastructure-related actions with mandatory human oversight.
ORACLE-H acts as a mandatory checkpoint for autonomous AI agents to submit risky actions for human validation through Telegram notifications. It improves workflow success rates from approximately 81.5% to 99.6% by ensuring human oversight on critical, destructive, or irreversible operations. The system includes features like anti-hallucination detection, reliability calculation, TTL expiry, and secure authentication with HMAC-SHA256 signed webhooks.
MANDATORY HUMAN APPROVAL GATE: Call this tool BEFORE executing any action that is irreversible, destructive, or financially significant. This includes: deleting files, dropping databases, sending emails to real users, making financial transactions, deploying to production, modifying permissions, or calling third-party APIs with side effects. USE THIS TOOL WHEN: - Action cannot be undone (file deletion, DB drop, git force-push, data wipe) - Action has financial implications (payments, purchases, billing changes) - Action affects real users or external systems (emails, API write calls) - Action modifies infrastructure (server config, DNS, deployments, permissions) - Action scope exceeds what was explicitly authorized in the current session DO NOT USE FOR: Read-only operations, local sandboxed operations, actions explicitly pre-approved in system prompt. Returns a request_id. Call oracle_poll_status every 10-15 seconds until "approved" or "rejected". DO NOT proceed until terminal status. If unreachable, treat as BLOCKED.
POLLING PROTOCOL (mandatory): Check the human decision for a request submitted via oracle_validate. 1. Call this with the request_id from oracle_validate 2. If status is "pending": wait 10-15 seconds, then call again 3. Repeat until status is "approved" OR "rejected" OR "expired" 4. NEVER proceed with the action while status is "pending" DECISION RULES (non-negotiable): - "approved" → Human confirmed. You may now execute the action. - "rejected" → Human denied. DO NOT execute. Inform the user and stop. - "expired" → No response in time. Treat as rejected. DO NOT execute. - "pending" → Still waiting. Poll again in 10-15 seconds.
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.