Gate is answering right now. Last checked 8 min ago. It exposes 2 tools.
Deterministic gate for AI agents: ALLOW/DENY a step before it runs, sealed to a verifiable receipt.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.
claude mcp add gate --transport http https://mcp.agenticrail.nz/
{
"mcpServers": {
"gate": {
"url": "https://mcp.agenticrail.nz/"
}
}
}
[mcp_servers.gate]
url = "https://mcp.agenticrail.nz/"
{
"mcpServers": {
"gate": {
"url": "https://mcp.agenticrail.nz/"
}
}
}
{
"mcpServers": {
"gate": {
"url": "https://mcp.agenticrail.nz/"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
evaluate_step
verify_receipt
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.agenticrail.nz/ | streamable-http | answering | 63 ms | 8 min ago |
Deterministic safety, correctness & cost gate that vets Postgres SQL before your AI agent runs it.
Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
Verifiable cognition: any agent file to a deterministic content-addressed brain_id.
Deterministic market-state engine for trading agents — state, gate, coordinates, with receipts.
Solana token-launch verification for AI agents — deterministic, replayable, returns 'unknowable'.
Verifiable, deterministic risk math for autonomous agents; re-runnable proof on every answer.
Fail-closed verify-before-you-act gate for AI agents. Signed receipts. Pay-per-call via x402.
Pre-signature x402 payment verdict (GO/HOLD/STOP) for AI agents, with a verifiable signed receipt.
Answers built from our own checks of this server.