LLM Latency Tracker for Cursor

dev.llmlatency/llm-latency-tracker

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

client:Cursor transport:streamable-http tools:2

Install LLM Latency Tracker in Cursor

~/.cursor/mcp.json · windows: %USERPROFILE%\.cursor\mcp.json

{
  "mcpServers": {
    "llm-latency-tracker": {
      "url": "https://llmlatency.dev/mcp"
    }
  }
}

Use .cursor/mcp.json in a project root instead to scope it to that project. Cursor merges both. Cursor docs