statlyte — live LLM pricing runs on your own machine — the client starts it, so there is no endpoint to ping. 32 installs a week from npm. Last commit 14 Aug 2026.
Live LLM pricing, context windows and model ids, read from each vendor's own page every 3 hours.
Today is the operative word: we check statlyte — live LLM pricing every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add statlyte -- npx -y statlyte
{
"mcpServers": {
"statlyte": {
"args": [
"-y",
"statlyte"
],
"command": "npx"
}
}
}
[mcp_servers.statlyte]
command = "npx"
args = ["-y", "statlyte"]
{
"mcpServers": {
"statlyte": {
"args": [
"-y",
"statlyte"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"statlyte": {
"args": [
"-y",
"statlyte"
],
"command": "npx"
}
}
}
Model Context Protocol server for live & historical sports stats and odds via ESPN.
Personal context for every AI: search, read, and write back to your private Markdown library.
Prices, context windows, lifecycle and deprecation dates for 270+ AI/LLM models. Daily, no key.
Continuity for agents: a live memory you can read and cite right now, outliving the context window.
Check if an AI model is deprecated, retiring, or silently changed price or context window.
Real-time web search and page fetch for AI agents from Andi's own index. LLM-ready markdown output.
Search and browse every MCP server in the Model Context Protocol registry.
Cross-LLM persistent memory: store context once, recall it from any AI model.
Answers built from our own checks of this server.