LLM Latency Tracker MCP server

Connect LLM Latency Tracker and your agent gets 2 tools, among them get_ai_api_latency, get_model_deprecations. It answers at https://llmlatency.dev/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 10 September 2026; the last check, on 19 October 2026, succeeded.

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

Description as the publisher wrote it.

The 2 tools LLM Latency Tracker offers

Add LLM Latency Tracker to your AI client

Every block below points at https://llmlatency.dev/mcp. Pick your client and copy.

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

{
  "mcpServers": {
    "llm-latency-tracker": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://llmlatency.dev/mcp"]
    }
  }
}

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

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

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

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

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

name: LLM Latency Tracker
version: 0.0.1
schema: v1
mcpServers:
  - name: LLM Latency Tracker
    type: streamable-http
    url: https://llmlatency.dev/mcp

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

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

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

goose://extension?url=https%3A%2F%2Fllmlatency.dev%2Fmcp&type=streamable_http&id=llm-latency-tracker&name=LLM%20Latency%20Tracker

Is LLM Latency Tracker up right now?

It answered our last check on 19 October 2026 in 228 ms. Over 6 checks since 10 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to LLM Latency Tracker

Questions about LLM Latency Tracker

Is there an official LLM Latency Tracker MCP server?

Yes. It is published by llmlatency.dev and served from llmlatency.dev, the vendor's own domain: https://llmlatency.dev/mcp.

How many tools does LLM Latency Tracker have?

2, as returned by the server's own tools/list on 11 September 2026: get_ai_api_latency, get_model_deprecations.

Is LLM Latency Tracker down?

It answered our last check on 19 October 2026 in 228 ms. Over 6 checks since 10 September 2026 it answered 6.

How do I add LLM Latency Tracker to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://llmlatency.dev/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does LLM Latency Tracker need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: dev.llmlatency. Endpoint host: llmlatency.dev. ARD identifier: urn:air:dev.llmlatency:mcp:llm-latency-tracker. First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.