Thoughtbox

{
  "title": "Thoughtbox MCP Observability",
  "description": "Generic MCP protocol observability dashboard",
  "tags": ["mcp", "observability", "opentelemetry"],
  "schemaVersion": 38,
  "version": 2,
  "refresh": "10s",
  "time": {
    "from": "now-1h",
    "to": "now"
  },
  "panels": [
    {
      "id": 1,
      "type": "stat",
      "title": "Upstream Status",
      "gridPos": { "h": 4, "w": 4, "x": 0, "y": 0 },
      "targets": [
        {
          "expr": "mcp_upstream_available",
          "legendFormat": "{{server_name}}"
        }
      ],
      "options": {
        "colorMode": "background",
        "graphMode": "none",
        "textMode": "value_and_name"
      },
      "fieldConfig": {
        "defaults": {
          "mappings": [
            { "value": 1, "text": "UP", "color": "green" },
            { "value": 0, "text": "DOWN", "color": "red" }
          ]
        }
      }
    },
    {
      "id": 2,
      "type": "stat",
      "title": "Request Rate (req/s)",
      "gridPos": { "h": 4, "w": 4, "x": 4, "y": 0 },
      "targets": [
        {
          "expr": "sum(rate(mcp_requests_total[1m]))"
        }
      ],
      "options": {
        "colorMode": "value",
        "graphMode": "area"
      }
    },
    {
      "id": 3,
      "type": "stat",
      "title": "Error Rate (5m)",
      "gridPos": { "h": 4, "w": 4, "x": 8, "y": 0 },
      "targets": [
        {
          "expr": "sum(rate(mcp_requests_total{status=\"error\"}[5m])) / sum(rate(mcp_requests_total[5m])) * 100"
        }
      ],
      "options": {
        "colorMode": "background",
        "graphMode": "none",
        "unit": "percent"
      },
      "fieldConfig": {
        "defaults": {
          "thresholds": {
            "mode": "absolute",
            "steps": [
              { "value": 0, "color": "green" },
              { "value": 1, "color": "yellow" },
              { "value": 5, "color": "red" }
            ]
          }
        }
      }
    },
    {
      "id": 4,
      "type": "stat",
      "title": "Active Connections",
      "gridPos": { "h": 4, "w": 4, "x": 12, "y": 0 },
      "targets": [
        {
          "expr": "mcp_active_connections"
        }
      ],
      "options": {
        "colorMode": "value",
        "graphMode": "area"
      }
    },
    {
      "id": 5,
      "type": "stat",
      "title": "p95 Latency",
      "gridPos": { "h": 4, "w": 4, "x": 16, "y": 0 },
      "targets": [
        {
          "expr": "histogram_quantile(0.95, sum by (le) (rate(mcp_request_duration_seconds_bucket[5m])))"
        }
      ],
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "unit": "s"
      },
      "fieldConfig": {
        "defaults": {
          "thresholds": {
            "mode": "absolute",
            "steps": [
              { "value": 0, "color": "green" },
              { "value": 1, "color": "yellow" },
              { "value": 5, "color": "red" }
            ]
          }
        }
      }
    },
    {
      "id": 6,
      "type": "timeseries",
      "title": "Requests by Method",
      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 4 },
      "targets": [
        {
          "expr": "sum(rate(mcp_requests_total[1m])) by (method)",
          "legendFormat": "{{method}}"
        }
      ],
      "options": {
        "legend": { "displayMode": "table", "placement": "right" }
      }
    },
    {
      "id": 7,
      "type": "timeseries",
      "title": "Requests by Status",
      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 4 },
      "targets": [
        {
          "expr": "sum(rate(mcp_requests_total[1m])) by (status)",
          "legendFormat": "{{status}}"
        }
      ],
      "options": {
        "legend": { "displayMode": "table", "placement": "right" }
      }
    },
    {
      "id": 8,
      "type": "timeseries",
      "title": "Latency Percentiles",
      "gridPos": { "h": 8, "w": 24, "x": 0, "y": 12 },
      "targets": [
        {
          "expr": "histogram_quantile(0.50, sum by (le) (rate(mcp_request_duration_seconds_bucket[5m])))",
          "legendFormat": "p50"
        },
        {
          "expr": "histogram_quantile(0.90, sum by (le) (rate(mcp_request_duration_seconds_bucket[5m])))",
          "legendFormat": "p90"
        },
        {
          "expr": "histogram_quantile(0.95, sum by (le) (rate(mcp_request_duration_seconds_bucket[5m])))",
          "legendFormat": "p95"
        },
        {
          "expr": "histogram_quantile(0.99, sum by (le) (rate(mcp_request_duration_seconds_bucket[5m])))",
          "legendFormat": "p99"
        }
      ],
      "fieldConfig": {
        "defaults": {
          "unit": "s"
        }
      }
    },
    {
      "id": 9,
      "type": "timeseries",
      "title": "Tool Calls by Tool Name",
      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 20 },
      "targets": [
        {
          "expr": "sum(rate(mcp_tool_calls_total[1m])) by (tool_name)",
          "legendFormat": "{{tool_name}}"
        }
      ],
      "options": {
        "legend": { "displayMode": "table", "placement": "right" }
      }
    },
    {
      "id": 10,
      "type": "timeseries",
      "title": "Tool Call Duration",
      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 20 },
      "targets": [
        {
          "expr": "histogram_quantile(0.95, sum by (le, tool_name) (rate(mcp_tool_duration_seconds_bucket[5m])))",
          "legendFormat": "{{tool_name}} p95"
        }
      ],
      "fieldConfig": {
        "defaults": {
          "unit": "s"
        }
      }
    },
    {
      "id": 11,
      "type": "timeseries",
      "title": "Resource Operations",
      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 28 },
      "targets": [
        {
          "expr": "sum(rate(mcp_resources_listed_total[1m]))",
          "legendFormat": "resources/list"
        },
        {
          "expr": "sum(rate(mcp_resource_reads_total[1m]))",
          "legendFormat": "resources/read"
        }
      ]
    },
    {
      "id": 12,
      "type": "timeseries",
      "title": "Message Throughput (bytes/s)",
      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 28 },
      "targets": [
        {
          "expr": "sum(rate(mcp_message_bytes_total[1m])) by (direction)",
          "legendFormat": "{{direction}}"
        }
      ],
      "fieldConfig": {
        "defaults": {
          "unit": "Bps"
        }
      }
    },
    {
      "id": 13,
      "type": "table",
      "title": "Top Methods by Request Count",
      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 36 },
      "targets": [
        {
          "expr": "topk(10, sum by (method) (increase(mcp_requests_total[5m])))",
          "format": "table",
          "instant": true
        }
      ],
      "transformations": [
        {
          "id": "organize",
          "options": {
            "excludeByName": { "Time": true },
            "renameByPattern": {
              "method": "Method",
              "Value": "Requests (5m)"
            }
          }
        }
      ]
    },
    {
      "id": 14,
      "type": "table",
      "title": "Top Tools by Call Count",
      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 36 },
      "targets": [
        {
          "expr": "topk(10, sum by (tool_name) (increase(mcp_tool_calls_total[5m])))",
          "format": "table",
          "instant": true
        }
      ],
      "transformations": [
        {
          "id": "organize",
          "options": {
            "excludeByName": { "Time": true },
            "renameByPattern": {
              "tool_name": "Tool",
              "Value": "Calls (5m)"
            }
          }
        }
      ]
    },
    {
      "id": 15,
      "type": "timeseries",
      "title": "Protocol Errors",
      "gridPos": { "h": 8, "w": 24, "x": 0, "y": 44 },
      "targets": [
        {
          "expr": "sum(rate(mcp_protocol_errors_total[1m])) by (error_code)",
          "legendFormat": "{{error_code}}"
        }
      ]
    }
  ]
}