LLM Latency Tracker MCP Server

Independent, provider-neutral latency & uptime for AI inference APIs - measured, not scraped. It is available as a remote MCP endpoint.

Teams that work with benchmark, latency and llms txt and want a hosted endpoint instead of running a local process. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-09-30 · ★ 2 · #115 OF 125 MAINTAINED DEVOPS & MONITORING · VERIFIED 2026-09-30

NOASSERTION · Python servers · how we verify → /methodology

01 · Install LLM Latency Tracker

before you install - you'll need

BASE_URL

Environment variables documented in the project's README - it lists which are required and which have defaults.

Claude Code

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

Claude Desktop / Cursor / VS Code - add to config

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

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

https://llmlatency.dev/mcp

transport: streamable-http

endpoint alive - responded to MCP initialize · probed 2026-09-30

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as remote - your agent's requests go to llmlatency.dev

endpoint auth accepted our unauthenticated MCP initialize - no credentials needed to connect

license no standard license detected - usage rights unclear; check the repo before commercial use

registry vendor namespace dev.llmlatency - domain-verified with the official MCP registry

03 · Who maintains LLM Latency Tracker

LLM Latency Tracker is maintained by mazamaka. It's the only MCP server we track from this author; the repo dates to Jul 2026.

04 · Facts

repository: github.com/mazamaka/llm-latency-tracker
website: https://llmlatency.dev/
category: DevOps & monitoring - ranked #115 of 125 actively-maintained DevOps & monitoring servers as of 2026-09-30.
registry: dev.llmlatency/llm-latency-tracker (active, first published 2026-07-23 · 2 versions)

05 · LLM Latency Tracker FAQ

What is LLM Latency Tracker?

Independent, provider-neutral latency & uptime for AI inference APIs - measured, not scraped. It is available as a remote MCP endpoint.

Is LLM Latency Tracker still maintained?

Yes - as of 2026-09-30, its last commit was 2026-09-30. We re-verify nightly.

How do I install LLM Latency Tracker?

Run `claude mcp add mazamaka-llm-latency-tracker --transport http https://llmlatency.dev/mcp`. The README documents one environment variable (BASE_URL) to set first. You can also paste the ready-made client config above.

Does LLM Latency Tracker require authentication?

No - the endpoint accepted our unauthenticated MCP initialize when probed on 2026-09-30; you can connect without credentials.

06 · Alternatives to LLM Latency Tracker

Alternatives to LLM Latency Tracker

Maintained DevOps & monitoring servers if LLM Latency Tracker isn't the fit.

Pairs well with

Servers that cover what LLM Latency Tracker doesn't - only shown when the pairing reason fits the companion.

More DevOps & monitoring MCP servers · LibreNMS MCP · Zabbix MCP · Raygun · GitLab CI MCP · Multimeter

More Python MCP servers · Voicemode · Okama MCP · Tenkai MCP · Hangar · MCPAmpel - MCP Security Scanner · see all