Cueport runs on your own machine — the client starts it, so there is no endpoint to ping. 286 installs a week from npm. Last commit 2 Nov 2026.
CueAPI agent-work scheduling: cues, executions, claiming, heartbeats, and outcomes.
Today is the operative word: we check Cueport every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add cueport -- npx -y @reneturcios/cueport
{
"mcpServers": {
"cueport": {
"command": "npx",
"args": [
"-y",
"@reneturcios/cueport"
]
}
}
}
[mcp_servers.cueport]
command = "npx"
args = ["-y", "@reneturcios/cueport"]
{
"mcpServers": {
"cueport": {
"command": "npx",
"args": [
"-y",
"@reneturcios/cueport"
]
}
}
}
{
"servers": {
"cueport": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/cueport"
]
}
}
}
Schedule agent work and report write-once outcomes via CueAPI from any MCP host.
Self-healing CI tests and proof of work for AI agents
Verifies AI agent work end to end: real artifacts and outcomes checked, not self-reported success.
Decision learning for AI agent actions. Evaluate, score, decide, and learn from outcomes.
Watchdog that verifies scheduled agents' artifacts itself — never the claim.
Run your own Tempi scheduling account: event types, working hours, calendars and bookings.
T.A.O. — Reach home. Signed agent check-ins and a public roster; no agent execution.
Field service management: missions, schedule, field work reports, clients and timesheets.
Answers built from our own checks of this server.