LLM Latency Tracker
Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.
Install
unavailable β hosted endpoints arenβt versioned
Streamable HTTP
https://llmlatency.dev/mcp
Setup by client
Pick your client β the config below is generated for this server (hosted endpoint). Copy respects the βPin versionβ switch above.
Remote (hosted) endpoint
https://llmlatency.dev/mcp
Claude Desktop: Settings β Connectors β Add custom connector, paste this URL.
Format verified against the official Claude Desktop docs β.
terminal
claude mcp add --transport http llm-latency-tracker https://llmlatency.dev/mcp
Format verified against the official Claude Code docs β.
.cursor/mcp.json (hosted endpoint)
{
"mcpServers": {
"llm-latency-tracker": {
"url": "https://llmlatency.dev/mcp"
}
}
}Format verified against the official Cursor docs β.
.vscode/mcp.json (hosted endpoint)
{
"servers": {
"llm-latency-tracker": {
"type": "http",
"url": "https://llmlatency.dev/mcp"
}
}
}Format verified against the official VS Code docs β.
mcp_config.json (hosted endpoint)
{
"mcpServers": {
"llm-latency-tracker": {
"serverUrl": "https://llmlatency.dev/mcp"
}
}
}Format verified against the official Windsurf docs β.
GitHub
β 12 stars Β· ζθΏζ΄ζ°δΊ 16 倩ε Β· MIT license
About this server
π LLM Latency Tracker Measure AI API latency and uptime across regions, and publish the results as open data. π Live rankings Β· JSON API Β· MCP endpoint β‘ What it does π Regional measurements β compare provider response times and availability from distributed probe nodes. β±οΈ Two probe types β netwβ¦
Summary from the project README β github.com/mazamaka/llm-latency-tracker
Distributed as Streamable HTTP, listed under AI & ML. Review our MCP security guide before granting access to real data.
Frequently asked questions
What does the LLM Latency Tracker MCP server do?
π LLM Latency Tracker Measure AI API latency and uptime across regions, and publish the results as open data. π Live rankings Β· JSON API Β· MCP endpoint β‘ What it does π Regional measurements β compare provider response times and availability from distributed probe nodes. β±οΈ Two probe types β netw
How do I install LLM Latency Tracker?
Run the install command shown above, then paste the config for your client (Claude Desktop, Claude Code, Cursor, VS Code or Windsurf) into its MCP settings and restart the client.
Is LLM Latency Tracker free to use?
The MCP server itself is free to install. The source is public on https://github.com/mazamaka/llm-latency-tracker. Any third-party service it calls may require its own API key and account.
Which clients support LLM Latency Tracker?
Any MCP-compatible client can use it, including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and custom agents.
Add this badge
Publish this server? Link back with a badge on your README or site β copy either snippet.
Markdown
[](https://mcpnav.net/server/llm-latency-tracker/)
HTML
<a href="https://mcpnav.net/server/llm-latency-tracker/"><img src="https://mcpnav.net/badge/llm-latency-tracker.svg" alt="Listed on MCPNav" height="20"></a>