The summary cards
Six cards sit at the top, reflecting the selected time range.The three middle cards are peaks, not totals. Each reports the highest count seen in any one period, so a window where ten servers were each busy at different hours shows the busiest hour’s count rather than ten.
Tool Calls
Every MCP message proxied in the period — not only tool invocations. The underlying query counts tool calls plus MCP protocol traffic (tools/list, initialize, and similar). A client that reconnects frequently, or an agent that enumerates tools before every run, inflates this relative to “things the agent actually did.”
For a count of genuine tool invocations, switch the Breakdown tab to group by Tool. Protocol traffic carries no tool name, so it is excluded there.
Error Rate
Requests that failed upstream plus requests blocked by policy or governance. Both land in this one figure, and the count beneath the percentage covers both. A spike is not necessarily a broken server — it may be a policy correctly denying traffic. The Errors tab breaks this down over time, both by server and as a rate.Avg Duration
The mean time per call spent on the MCP server, as measured at the gateway. The timer starts when the gateway sends your request upstream and stops when the server’s response comes back, so the figure is time attributable to the server and the network between it and the gateway.The card is named duration, not latency, because it is the whole call’s wall-clock — not the overhead Barndoor adds on top. It is not a number to subtract from anything.
It’s a mean, not a percentile, so one slow call skews a quiet server. A server with four calls — three at 100ms and one at 30s — reports 7.6s, which describes none of them.
The tabs
Trends
Tool calls, average duration, and active users over time. The period length follows the selected range, so a wider window means coarser periods.Errors
Two views side by side: error count over time stacked by MCP server, and error rate as a percentage. The stack answers “is one server responsible?”; the rate answers “how bad is it relative to volume?” On low traffic these can disagree — a handful of errors is a low count but a high rate. That is expected, and the rate is usually the one to act on.By period
One row per period — hourly, daily or weekly, chosen from the Usage by dropdown — with tool calls, duration, errors and active users for each. Options that would be unreadable for the selected range (hourly over a month, weekly over a day) are greyed out. Expanding a row breaks that single period down along the dimension set in Expand to, so you can go from “Tuesday was bad” to “Tuesday was bad on this server” without changing the date range.Breakdown
The same traffic grouped along one dimension at a time — MCP Server, Tool, User, or AI Agent — with tool calls, average duration, and errors per row. The metric definitions above apply unchanged. Rows are grouped by name, so a server renamed mid-period appears as two rows. The table returns at most 500 groups, ordered by tool call volume. Only very large or very broad selections reach that, and grouping by Tool over a wide window is the likeliest way to hit it — narrow the date range if you need the tail.Frequently asked
Why is one server's duration in milliseconds and another's in seconds?
Why is one server's duration in milliseconds and another's in seconds?
Usually because the calls genuinely differ. An in-cluster server has a far shorter network path than an external SaaS API, and cheap lookups finish faster than heavy queries. Compare each server against its own history rather than against other servers.
Why does Tool Calls exceed the number of tool calls I expect?
Why does Tool Calls exceed the number of tool calls I expect?
It includes MCP protocol traffic —
tools/list, initialize, and similar — not only tool invocations. Agents that reconnect or re-enumerate tools frequently generate a lot of this. Grouping by Tool on the Breakdown tab excludes it.My error rate spiked but the server looks healthy.
My error rate spiked but the server looks healthy.
Policy denials count as errors. Check the Errors tab to see whether the spike concentrates on one server, and whether it coincides with a policy change rather than an upstream fault.
Can I filter the dashboard to one team or agent?
Can I filter the dashboard to one team or agent?
Not currently. The Breakdown and By period tabs group by user or AI agent, so per-agent figures are visible in a table, but the summary cards and charts always cover all organization traffic. Scoping the whole dashboard to a single team, user, or agent is on the roadmap.