Raposa Aval

Human approval for AI agents.

CommunityOnlineNo sign-inRU / CISFreeRead-only

What it can do

  • Create Approval: Create an approval request and return its id immediately (no waiting). Use with a webhook_url, or poll with get_approval. risk: low | medium | high.
  • Get Approval: Read an approval by id. Look at `approved` — it is true only when a human approved.
  • Request Human Approval: Ask an authorised human to approve an action and wait for the answer (up to wait_sec, max 50). Returns {approved: bool, status, decided_by, ...}. Proceed ONLY if approved is tr

What data it sees

Do you need an account

No: the server works without sign-in

Human approval for AI agents. request_human_approval(action, context, risk) pauses a high-stakes action (refund, payout, deploy, deletion) until a named person approves or rejects in the console, by email, Telegram or Slack. Silence is not consent: a timeout, expiry or rejection returns approved=false. Every decision is sealed in a hash-chained audit log you can export. EU-hosted (Germany), DPA available. Free sandbox key (100 approvals/month): https://raposa.group/start/

Server tool list (3)

Raw names from tools/list. Only developers need these.

create_approvalCreate an approval request and return its id immediately (no waiting). Use with a webhook_url, or poll with get_approval. risk: low | medium | high.
get_approvalRead an approval by id. Look at `approved` — it is true only when a human approved.
request_human_approvalAsk an authorised human to approve an action and wait for the answer (up to wait_sec, max 50). Returns {approved: bool, status, decided_by, ...}. Proceed ONLY if approved is true — a timeout, an expiry or a rejection means do not proceed. On timeout the request stays open: check later with get_approval. risk: low | medium | high.