Consistency Gate is answering right now. Last checked 14 min ago. It exposes 3 tools.
Check claims against a fact-store: consistent, contradicts, or unverifiable — with a receipt.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.
claude mcp add consistency-gate --transport http https://mcp.humanified.dk/mcp
{
"mcpServers": {
"consistency-gate": {
"url": "https://mcp.humanified.dk/mcp"
}
}
}
[mcp_servers.consistency-gate]
url = "https://mcp.humanified.dk/mcp"
{
"mcpServers": {
"consistency-gate": {
"url": "https://mcp.humanified.dk/mcp"
}
}
}
{
"mcpServers": {
"consistency-gate": {
"url": "https://mcp.humanified.dk/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
check_claim
list_facts
check_triple
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.humanified.dk/mcp | streamable-http | answering | 143 ms | 14 min ago |
Real-time fact-checking MCP. Verifies claims against live sources with structured verdicts.
Verified memory for coding agents: claims cited against code, stale withheld, savings receipts.
Pre-signature x402 payment verdict (GO/HOLD/STOP) for AI agents, with a verifiable signed receipt.
Fact-check claims against live web sources: verdict, consensus, cited sources, PII redaction.
Fact-check claims against independent sources — fast verdict or deep multi-step investigation.
Verify claims with web evidence. Returns sources and verdict. x402 micropayment.
Human-in-the-loop approval for agent actions, with verifiable action-bound receipts.
Cost-parity bench for agent loops: $/success and time across model mixes, with verifiable receipts.
Answers built from our own checks of this server.