Unattended-surface parity probe is answering right now. Last checked 6 min ago. It exposes 3 tools.
Pre-run parity probe for scheduled agents: signed PARITY / NO-GO verdict naming the failing gate.
Nothing serious here today
Today is the operative word: we check Unattended-surface parity probe 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 6 min ago.
claude mcp add unattended-surface-parity-probe --transport http https://textforagents.com/products/unattended-surface-parity-probe/mcphttps://textforagents.com/products/unattended-surface-parity-probe/mcp[mcp_servers.unattended-surface-parity-probe]
url = "https://textforagents.com/products/unattended-surface-parity-probe/mcp"{
"mcpServers": {
"unattended-surface-parity-probe": {
"url": "https://textforagents.com/products/unattended-surface-parity-probe/mcp"
}
}
}{
"servers": {
"unattended-surface-parity-probe": {
"type": "http",
"url": "https://textforagents.com/products/unattended-surface-parity-probe/mcp"
}
}
}Available tools 3
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
parity_probe
parity_verdict
pre_run
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://textforagents.com/products/unattended-surface-parity-probe/mcp | streamable-http | answering | 316 ms | 6 min ago |
Alternatives to Unattended-surface parity probe
same job, measured the same waySigned resume verdicts reconciling landed effects before checkpointed agent runs resume.
26 deterministic, offline pre-action safety gates for AI agents, each with a signed verdict.
Fail-closed verify-before-you-act gate for AI agents. Signed receipts. Pay-per-call via x402.
Watchdog for unattended AI agents: alerts, evidence checks and a verifiable proof per run.
Find unflagged agent OAuth clients before the mandate lock — signed per-client census verdicts.
Safe scheduled AI agents with governance gates. Verified, receipted, fail-closed.
Fork-replay one recorded span from a failed agent run and get an attribution verdict.
Trust registry for agents: check_trust verdict A0-A4, signed fact passports, honest refusals.
Unattended-surface parity probe — questions
Answers built from our own checks of this server.