MCP Server
MCP
LLM Latency Tracker
Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.
Configuration Example
{
"remotes": [
{
"type": "streamable-http",
"url": "https://llmlatency.dev/mcp"
}
],
"packages": []
}
mcp
model-context-protocol
streamable-http
By
Comments
Sign in to leave a comment