MCP Server

LLM Latency Tracker

dev.llmlatency/llm-latency-tracker
Data & Analytics Public & reachable MCP 2026-07-28

What this MCP does

Provides regional latency and uptime metrics for AI inference APIs and tracks model deprecations.

get_ai_api_latency
Measured latency (TTFB p50/p95) and uptime rankings of AI inference API providers by region, from llmlatency.dev.
Input schema
{'type': 'object', 'properties': {'region': {'type': 'string', 'description': 'eu-hetzner, us-central, ap-tokyo or sa-east; omit for all'}}}
get_model_deprecations
AI model deprecation calendar: announced and shutdown dates, replacement models, and how many days of migration notice each provider actually gives (median/min/max). Every entry is verified against the provider own deprecation page.
Input schema
{'type': 'object', 'properties': {'provider': {'type': 'string', 'description': 'openai, anthropic, google, mistral, cohere, azure-openai; omit for all'}}}
Added
get_model_deprecations
Sept. 17, 2026, 12:39 p.m.
Added
get_ai_api_latency
Sept. 17, 2026, 12:39 p.m.