LLM Latency Tracker — Claude Code MCP server: how to install
Tracks regional TTFB, time to first token, and uptime for AI inference endpoints. It helps agents find the fastest available model provider.
claude mcp add --transport http llm-latency-tracker https://llmlatency.dev/mcpWhat LLM Latency Tracker does
The server exposes regional latency metrics and provider uptime directly to coding agents. It compiles network responsiveness (TTFB) alongside inference timing (TTFT), grouping numbers by geographic zones with p50 and p95 percentiles.
All provided tools are strictly read-only. The server includes get_ai_api_latency for regional leaderboards, get_provider_latency for specific providers, get_model_deprecations for retirement schedules, and get_coding_agent_health to observe agent drift.
Edge TTFB measures connection latency rather than token output velocity. Connecting to the public endpoint at https://llmlatency.dev/mcp requires zero API credentials.
What it helps with
- Compare latency metrics across AI providers within a target region
- Check scheduled deprecation dates for LLM models
- Retrieve p50 and p95 TTFB benchmarks for a selected provider
- Inspect speed and accuracy trends for coding agents
Example prompts for the agent
- Find the lowest latency AI providers in Europe using
get_ai_api_latency - Check upcoming model shutdowns with
get_model_deprecations - Look up p50 and p95 metrics for fireworks across all regions
How to install LLM Latency Tracker
Platform CLI: remote server
claude mcp add --transport http llm-latency-tracker https://llmlatency.dev/mcpPlatform CLI: remote server
codex mcp add llm-latency-tracker --url https://llmlatency.dev/mcpConfig file
{
"mcpServers": {
"llm-latency-tracker": {
"url": "https://llmlatency.dev/mcp"
}
}
}Config file
{
"servers": {
"llm-latency-tracker": {
"type": "http",
"url": "https://llmlatency.dev/mcp"
}
}
}Platform CLI: remote server
gemini mcp add -t http llm-latency-tracker https://llmlatency.dev/mcpStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about LLM Latency Tracker
How to install LLM Latency Tracker in Claude Code?
Run claude mcp add --transport http llm-latency-tracker https://llmlatency.dev/mcp. This connects your agent directly to the public HTTP endpoint.
What does LLM Latency Tracker do?
It gives your coding agent read-only access to regional availability, TTFB, and first-token latency statistics across dozens of AI inference hosts.
Are provider API keys required?
No keys are needed when querying the public MCP endpoint. You only need API keys if you execute your own inference measurement probes locally.
