LLM Latency Tracker for VS Code

dev.llmlatency/llm-latency-tracker

Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.

client:VS Code transport:streamable-http tools:2

Install LLM Latency Tracker in VS Code

.vscode/mcp.json

{
  "servers": {
    "llm-latency-tracker": {
      "type": "http",
      "url": "https://llmlatency.dev/mcp"
    }
  }
}

Requires agent mode. MCP: Open User Configuration puts the same block in every workspace. VS Code docs