LLM Latency Tracker for Claude Code
dev.llmlatency/llm-latency-tracker
Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.
client:Claude Code
transport:streamable-http
tools:2
Install LLM Latency Tracker in Claude Code
run in your project directory
claude mcp add --transport http llm-latency-tracker https://llmlatency.dev/mcpAdds it for this project only. Append --scope user to make it available everywhere. Claude Code docs