Regent Protocol is answering right now. Last checked moments ago.
Spending control for AI agents: approved budgets, a decision before each payment, signed receipts.
Nothing serious here today
Today is the operative word: we check Regent Protocol every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.
claude mcp add cloud-gateway --transport http https://gw.regentprotocol.org/gw/mcphttps://gw.regentprotocol.org/gw/mcp[mcp_servers.cloud-gateway]
url = "https://gw.regentprotocol.org/gw/mcp"{
"mcpServers": {
"cloud-gateway": {
"url": "https://gw.regentprotocol.org/gw/mcp"
}
}
}{
"servers": {
"cloud-gateway": {
"type": "http",
"url": "https://gw.regentprotocol.org/gw/mcp"
}
}
}Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://gw.regentprotocol.org/gw/mcp | streamable-http | answering | 453 ms | 0 min ago |
Alternatives to Regent Protocol
same job, measured the same wayPolicy decision point for agent payments — allow, ask, or veto before signing
Allow, ask, or veto — a policy decision point your agent consults before signing any payment
Pink Agentic AI Payments: AI agents pay within spending rules (budgets, caps, approval). Sandbox.
Web search for agents, one x402 payment: real results, provider failover, signed receipt. $0.01.
Pre-payment safety gate for x402 agents: PII screening, spend policy, replay checks before signing.
Budgets, propose-then-approve, and receipts for agents that buy for a human. Dry-run by default.
Authorize x402 payments before signing with request-bound, signed safety decisions.
AI agent payments with human approval. Local-first, encrypted credentials, budget controls.
Regent Protocol — questions
Answers built from our own checks of this server.