Tool reference

Every tool the Rius MCP server exposes, with arguments and example invocations. All tools return Markdown, which your client renders as tables and summaries. Everything is read-only with one exception, create_api_key, which is admin-gated.

Two conventions apply across the trace tools:

• workspace is optional everywhere: pass a workspace name or ID, or omit it to use your default workspace. Discover workspaces with list_workspaces.
• hours is a lookback window ending now (default 24). “This week” is hours: 168.

agent_traces_summary

Summary KPIs for agent traces over a time window: trace count, LLM calls, error rate, total/average cost, token usage, and latency percentiles (p50/p95/p99).

How did my agents do over the last 24 hours?

{ "name": "agent_traces_summary", "arguments": { "hours": 24 } }

Summarize the checkout-agent service this week.

{ "name": "agent_traces_summary", "arguments": { "hours": 168, "service": "checkout-agent" } }

create_api_key

Create a new API key in one of your workspaces. Requires admin access in that workspace. The plaintext key is shown exactly once in the response. It is never retrievable again after this call, so save it immediately.

Not available when this MCP connection is itself authenticated with an API key (headless mode): a leaked agent key must not be able to mint more keys. Mint keys from an interactive (OAuth) session or the console instead.

Create an API key so this agent can send traces.

{ "name": "create_api_key", "arguments": { "name": "my-agent" } }

Give it a key that can query the API too.

{ "name": "create_api_key", "arguments": { "scopes": ["ingest", "read"] } }

get_agent_trace

Get one agent trace’s span waterfall (spans in time order, indented by depth).

Captured content is subject to the workspace’s privacy controls: spans exported with capture_content=False or a mask have nothing extra to show.

Break down trace 4bf92f3577b34da6a3ce929d0e0e4736 for me.

{ "name": "get_agent_trace", "arguments": { "trace_id": "4bf92f3577b34da6a3ce929d0e0e4736" } }

What did the LLM actually say in that failed span?

{ "name": "get_agent_trace", "arguments": { "trace_id": "4bf92f3577b34da6a3ce929d0e0e4736", "include_content": true } }

get_me

Get your own identity and access context.

Returns your user (id, external id, email), your organization (id, name) and your role in it (“admin” or “member”), and the workspaces you can access. If you have not yet joined an organization (for example, a pending invite that has not been accepted), the organization and role are reported as “none”. On a connection authenticated with an API key rather than a login, only the workspaces are reported — a key has no user or organization of its own.

No arguments.

Who am I in Rius?

{ "name": "get_me", "arguments": {} }

list_agent_traces

List recent agent traces (one row per trace) newest-first, as a Markdown table.

The trace_id column feeds get_agent_trace. When more traces exist than limit, the reply says so; narrow the window or add a filter rather than raising the limit past what a chat can usefully display.

Show me the failed runs from the last two days.

{ "name": "list_agent_traces", "arguments": { "hours": 48, "status": "Error" } }

list_metrics_catalog

List every metric the platform knows how to compute, with its unit, nullability, which endpoint serves it, and its companions (the extra response keys it contributes: coverage keys for scalars, row/point value keys for breakdowns and series). Use it to discover exact field names instead of guessing them.

What latency metrics exist?

{ "name": "list_metrics_catalog", "arguments": { "group": "latency" } }

list_workspaces

List the workspaces you have access to (id and name).

Use it to find the right value for the workspace argument of the trace and metrics tools.

No arguments.

Which Rius workspaces do I have?

{ "name": "list_workspaces", "arguments": {} }

workspace_metrics_overview

Aggregated health of a whole workspace over a time window: the numbers behind the dashboard’s overview: volume (traces/spans/LLM calls), cost, tokens, latency percentiles, TTFT, error rates, each with its previous-window baseline and delta, plus ranked breakdowns (per model, top agents, calls by kind, top exceptions, slowest spans).

Use this to answer “how is my workspace doing” before drilling into individual traces with list_agent_traces / get_agent_trace.

Values are milliseconds for latency/TTFT; — means not measured (null), which is never the same as a measured 0. Metrics listed as degraded failed to compute and are absent rather than zero.

How is my workspace doing today?

{ "name": "workspace_metrics_overview", "arguments": {} }

Anything wrong in the last 10 minutes?

{ "name": "workspace_metrics_overview", "arguments": { "minutes": 10 } }

Next steps

• Example workflows: the trace tools composed into complete investigations.
• Quick connect: connecting a client if you have not yet.