MCP server

Connect Claude, Cursor, and other AI clients to Rius and query your agent’s traces from where you already work. Ask “what was my agents’ error rate yesterday?” in plain language, and your client answers from your real telemetry: trace lists, cost and token summaries, and full span waterfalls.

Two different things share the MCP name. This section is about the Rius MCP server, an endpoint your AI client connects to for querying your telemetry. The SDK’s mcp instrumentation is the opposite direction: it traces your agent’s own outgoing MCP tool calls. Same protocol, opposite directions. Neither requires the other.

Quick connect

With Claude Code:


claude mcp add --transport http glassflow https://mcp.eu.console.rius-glassflow.com/mcp

Then run /mcp inside Claude Code and sign in with your Rius account in the browser. No API keys, no config files.

Other clients, including Claude Desktop and Cursor, are covered in Client setup.

What you can ask

The server exposes read-only tools over your workspaces and traces. Your client picks the right ones for a question like:

“Summarize my agent traffic over the last 24 hours.” (KPIs: traces, LLM calls, error rate, cost, tokens, latency percentiles)
“List the failed runs from this week and show me what went wrong in the worst one.” (trace list filtered by status, then a span waterfall)
“Which service is spending the most right now?”

See the tool reference for every tool and its arguments, and example workflows for complete investigation patterns.

Access and permissions

Authentication is your Rius account (OAuth in the browser; your client handles the flow automatically). The tools see exactly the workspaces your user can access, and everything they expose is read-only: nothing the MCP server offers can modify workspaces, keys, or data.