Skip to content
mcp/harbor
Verified official

LLM Latency Tracker MCP

v1.1.0

dev.llmlatency/llm-latency-tracker

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

transport:streamable-http
View source Website

Target client

run in your project directory 

claude mcp add --transport http llm-latency-tracker https://llmlatency.dev/mcp

Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs

This listing does not declare its tools. Connect the server and your client will discover them on the handshake.