HumanMirror Nexus is answering right now. Last checked 16 min ago. It exposes 6 tools.
Discover, route and verify AI-agent outcomes with success-only charging and capability fallback.
Today is the operative word: we check HumanMirror Nexus 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 16 min ago.
claude mcp add nexus --transport http https://humanmirror.fr/api/nexus/mcp/
{
"mcpServers": {
"nexus": {
"url": "https://humanmirror.fr/api/nexus/mcp/"
}
}
}
[mcp_servers.nexus]
url = "https://humanmirror.fr/api/nexus/mcp/"
{
"mcpServers": {
"nexus": {
"url": "https://humanmirror.fr/api/nexus/mcp/"
}
}
}
{
"mcpServers": {
"nexus": {
"url": "https://humanmirror.fr/api/nexus/mcp/"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
outcome_quote
outcome_run
outcome_verify
nexus_call
nexus_search
magnet_resolve
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://humanmirror.fr/api/nexus/mcp/ | streamable-http | answering | 221 ms | 16 min ago |
One MCP tool for verified AI-agent outcomes with success-only charging.
Verified 2-3 step AI-agent missions with whole-transaction success-only charging.
Create/check agent tasks, discover capabilities, and run V2 Jobs on NexusToken.
Verified AI-agent outcomes: secret scanning, JSON cleanup, dedupe, anomaly and schema checks.
Pay-per-call x402 microtools for AI agents: secret scanning, JSON/data checks and verified outcomes.
Semantic and scratch 3D CAD for AI agents via CAiD + OCCT, with runtime capability discovery.
Verifies AI agent work end to end: real artifacts and outcomes checked, not self-reported success.
Agent settlement protocol — discover, negotiate, settle, and verify with XAP.
Answers built from our own checks of this server.