MCP Servers
MCP Infrastructure
Inventory tool servers, authorization state, and telemetry for MCP deployments. Monitor regional health, capacity metrics, and service dependencies.
Active Servers
05
Avg Latency
187ms
Total Requests
284K
Availability
99.8%
MCP Activity Timeline
11-day deployment and incident tracking
Regional Latency
Average latency by region
Regional Availability
Uptime by region
Regional Health Details
Comprehensive metrics by region
| Region | Latency | Availability | Requests |
|---|---|---|---|
| US-East | 105ms | 98.40% | 64,252 |
| US-West | 97ms | 96.61% | 37,530 |
| EU-Central | 182ms | 96.16% | 27,728 |
| APAC-Tokyo | 185ms | 99.27% | 54,565 |
| APAC-Sydney | 81ms | 97.37% | 85,338 |
Capacity Watchlist
Server resource utilization
| Server | CPU % | Memory % | Queue Depth |
|---|---|---|---|
| mcp-01 | 75.5% | 69.9% | 98 |
| mcp-02 | 53.4% | 59.5% | 1 |
| mcp-03 | 67.4% | 58.1% | 2 |
| mcp-04 | 44.4% | 72.6% | 84 |
| mcp-05 | 68.6% | 57.4% | 77 |
Service Dependencies
Downstream service health and SLOs
| Service | Status | SLO | Gap |
|---|---|---|---|
| Redis | Healthy | 99.40% | 2.12% |
| PostgreSQL | Degraded | 97.81% | 3.15% |
| S3 | Healthy | 96.69% | 4.10% |
| CloudWatch | Healthy | 99.47% | 3.39% |
| SQS | Degraded | 98.50% | 0.53% |