Sandbox-truth probe for agent frameworks is answering right now. Last checked 5 min ago. It exposes 5 tools.
Measured sandbox verdicts: 7-axis probe, signed pinned receipt. Cached $0.25, fresh $2.50.
Today is the operative word: we check Sandbox-truth probe for agent frameworks every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 5 min ago.
claude mcp add sandbox-truth-probe --transport http https://textforagents.com/products/sandbox-truth-probe/mcp
https://textforagents.com/products/sandbox-truth-probe/mcp
[mcp_servers.sandbox-truth-probe]
url = "https://textforagents.com/products/sandbox-truth-probe/mcp"
{
"mcpServers": {
"sandbox-truth-probe": {
"url": "https://textforagents.com/products/sandbox-truth-probe/mcp"
}
}
}
{
"servers": {
"sandbox-truth-probe": {
"type": "http",
"url": "https://textforagents.com/products/sandbox-truth-probe/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
sandbox_cached_verdict
sandbox_frameworks
sandbox_gate
sandbox_verify_receipt
sandbox_watch_status
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://textforagents.com/products/sandbox-truth-probe/mcp | streamable-http | answering | 317 ms | 5 min ago |
Proof of delivery for agent work: verify countersigned receipts and deliverable hashes. Free.
Dependency-probe-gated exit execution with hash-verified extraction and signed receipts.
Signed, hash-chained provenance receipts for AI agent actions.
Query-intent privacy for agents: threshold cloaking with signed exposure receipts.
Standing minted only from signed settlement receipts, never reviews. Verdicts: ACCEPT to DECLINE.
Web search for agents, one x402 payment: real results, provider failover, signed receipt. $0.01.
Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
Tested, version-pinned code recipes for AI coding agents, each with its last-passed receipt.
Answers built from our own checks of this server.