Rius is answering right now. Last checked 1 min ago. Last commit 22 Oct 2026.
Query your AI agents' traces, errors, cost and alerts in Rius, the agent observability platform.
Today is the operative word: we check Rius 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 1 min ago.
claude mcp add rius --transport http https://mcp.eu.console.rius-glassflow.com/mcp
https://mcp.eu.console.rius-glassflow.com/mcp
[mcp_servers.rius]
url = "https://mcp.eu.console.rius-glassflow.com/mcp"
{
"mcpServers": {
"rius": {
"url": "https://mcp.eu.console.rius-glassflow.com/mcp"
}
}
}
{
"servers": {
"rius": {
"type": "http",
"url": "https://mcp.eu.console.rius-glassflow.com/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.eu.console.rius-glassflow.com/mcp | streamable-http | sign-in | 151 ms | 1 min ago |
MCP observability. Query live traffic, errors, duration, and alerts from your AI agent.
Manage Sable AI voice agents, query HyperDX logs and metrics, and deploy — all from your IDE
Observability MCP server: query LLM cost/errors/latency & operate alerts/evals from Claude/Cursor
Structured observability for AI agents. Trace steps, decisions, and errors. MCP server + CLI viewer.
AI agent observability for production traces, natural-language insights, and improvement loops.
Observability for AI apps: investigate traces, logs, LLM usage, replays and crashes; manage alerts.
Query Honeycomb observability data: traces, events, metrics, SLOs, triggers, and boards.
Observability for incident agents — query Loki (LogQL), Prometheus (PromQL), Elasticsearch.
Answers built from our own checks of this server.