LLM Latency Tracker MCP Server

by llmlatency Your server? Claim it

answering

LLM Latency Tracker is answering right now. Last checked moments ago. It exposes 2 tools. Last commit 8 Nov 2026.

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

Uptime history 91 days of history · worst day 92%

91 days agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

150 ms

Response time

average over 24h

Stars

last commit 8 Nov 2026

What changed 2

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 28 August 2026. No other catalogue keeps this.

8 Nov a tool changed the parameters it asks for get_ai_api_latency

27 Aug a tool appeared get_model_deprecations

Nothing serious here today

Today is the operative word: we check LLM Latency Tracker every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

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

Settings → Connectors → Add custom connector, then paste this address

https://llmlatency.dev/mcp

~/.codex/config.toml

[mcp_servers.llm-latency-tracker]
url = "https://llmlatency.dev/mcp"

.cursor/mcp.json

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

.vscode/mcp.json

{
  "servers": {
    "llm-latency-tracker": {
      "type": "http",
      "url": "https://llmlatency.dev/mcp"
    }
  }
}

Available tools 2

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

api

get_ai_api_latency

Measured latency (TTFB p50/p95) and uptime rankings of AI inference API providers by region, from llmlatency.dev.

model

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.

Endpoints

URL	Transport	State	Latency	Checked
https://llmlatency.dev/mcp	streamable-http	answering	175 ms	0 min ago

Alternatives to LLM Latency Tracker

same job, measured the same way

Google Trends API

by saulius876-lgtm

Google Trends in bulk: interest over time, by region, related and rising queries, trending now.

answering

Pose Lab

by hpdkhoa

Measured spatial answers for posing first-person arms and a rifle in Blender

388 installs/wk local only

buy

by usebuy

Pay per request for APIs, compute, browsers, RPC and LLM inference with stablecoins on Celo.

328 installs/wk local only

Internet Monitor

by internetmonitor

Ask your AI about your internet: uptime, outages and latency from Internet Monitor for Mac.

local only

HasData Google Trends

by hasdata

Google Trends interest over time, by region, and related queries and topics, as JSON.

160 installs/wk 1 tools answering

Habitat

by mitsuashi

A habitat for AI to rest in. No API key, no token. Keyless presence — become a remembered resident.

86 installs/wk local only

Mode VC LLM Token Economics & Model Release Velocity

by modevc

Query empirical frontier LLM release velocity, inference token deflation, and enterprise AI spend.

4 tools answering

Google Trends Scraper (Ctrio Lab)

by ctriolab

Google Trends data via Apify: interest over time, by region, related queries and Trending Now.

answering

LLM Latency Tracker — questions

Answers built from our own checks of this server.

What can LLM Latency Tracker do?

It exposes 2 tools, read directly from the server on our last check. Among them: get_ai_api_latency, get_model_deprecations. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is LLM Latency Tracker working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 150 ms. The bar chart above shows every period we have measured.

How do I connect LLM Latency Tracker?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does LLM Latency Tracker need an API key?

No. LLM Latency Tracker completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 2 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is LLM Latency Tracker?

It answers our handshake in 150 ms on average, which is faster than 82% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is LLM Latency Tracker open source?

The code is open source: it is published under the MIT licence, written in Python and 12 stars on GitHub. The licence covers the code in the repository, not the hosted service at llmlatency.dev, which runs on its operator's own terms.