Skip to content

LLM Latency Tracker

by llmlatency.dev · remote · no sign-in to list tools · v1.1.0 · published by dev.llmlatency

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

Read only
CompareRegistry entry

2 tools: 2 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

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

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

2 tools

Only reads 2Claude Code: allow
  • get_ai_api_latencyMeasured latency (TTFB p50/p95) and uptime rankings of AI inference API providers by region, from llmlatency.dev.No findings

    Why it is in this group

    • The name "get_ai_api_latency" says "get": a word for reading.
    Description, as the server wrote it
    Measured latency (TTFB p50/p95) and uptime rankings of AI inference API providers by region, from llmlatency.dev.
  • get_model_deprecationsAI model deprecation calendar: announced and shutdown dates, replacement models, and how many days of migration notice each provider actually gives (median/min/max).Reads private dataNo findings

    Why it is in this group

    • The name "get_model_deprecations" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "calendar": it reads calendars.
    Description, as the server wrote it
    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.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Looked at Oct 22, 2026, 14:46 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
0
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
none
RFC 9728 protected resource metadata
none
Authorization servers
none
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__llm-latency-tracker__get_ai_api_latency",
      "mcp__llm-latency-tracker__get_model_deprecations"
    ],
    "ask": [],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as llm-latency-tracker. Review it before you use it.

Capability tags behind 1 rule
  • mcp__llm-latency-tracker__get_model_deprecations private-data