Skip to main content
The Servers page in Ultra Hub provides visibility into all upstream MCP servers used across your organization. See which servers are active, how they’re performing, and who’s using them.

Server List

The main view shows a card for each MCP server with key metrics:
MetricDescription
Server NameThe configured name of the upstream server
Request CountTotal number of MCP requests handled
Success RatePercentage of requests that completed successfully
Unique ToolsNumber of distinct tools called on this server
Avg LatencyAverage response time in milliseconds
GatewaysNumber of gateways routing traffic to this server
UsersNumber of users interacting with this server
Click any server card to view detailed information.

Server Detail View

The detail view provides in-depth metrics and breakdowns for a single server.

Stats Overview

At the top, summary cards show:
  • Total Requests — Lifetime request count
  • Success Rate — Overall success percentage
  • Errors — Total error count
  • Tools — Number of unique tools available
  • Avg Latency — Average response time

Tools Tab

A table of every tool called on this server:
ColumnDescription
Tool NameThe MCP tool identifier
CallsTotal number of times this tool was called
SuccessNumber of successful calls
ErrorsNumber of failed calls
Avg LatencyAverage response time for this tool
Use this to identify your most-used tools, spot error-prone tools, and find performance bottlenecks.

Gateways Tab

Shows which gateways are routing traffic to this server:
ColumnDescription
GatewayGateway name
RequestsTotal requests from this gateway
SuccessSuccessful request count
ErrorsError count
Avg LatencyAverage latency from this gateway

Users Tab

Shows which users are interacting with this server:
ColumnDescription
UserUser name or email
RequestsTotal requests from this user

Requests Tab

A full paginated trace history for this server. Each entry links to the detailed trace view. Use Load More to page through older requests.

Use Cases

  • Performance monitoring — Identify slow servers or tools that need optimization
  • Usage analysis — Understand which servers and tools your team relies on most
  • Troubleshooting — Drill into error patterns by server, tool, gateway, or user
  • Capacity planning — Track request volumes and gateway counts to plan infrastructure