Kosha Model Discovery runs on your own machine — the client starts it, so there is no endpoint to ping. 2 058 installs a week from npm. Last commit 4 Nov 2026.
Tells your agent which model to use and what it costs, across 46 providers and local runtimes.
Today is the operative word: we check Kosha Model Discovery 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 kosha-discovery -- npx -y @sriinnu/kosha-discovery
{
"mcpServers": {
"kosha-discovery": {
"command": "npx",
"args": [
"-y",
"@sriinnu/kosha-discovery"
]
}
}
}
[mcp_servers.kosha-discovery]
command = "npx"
args = ["-y", "@sriinnu/kosha-discovery"]
{
"mcpServers": {
"kosha-discovery": {
"command": "npx",
"args": [
"-y",
"@sriinnu/kosha-discovery"
]
}
}
}
{
"servers": {
"kosha-discovery": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@sriinnu/kosha-discovery"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
ANTHROPIC_API_KEY (Anthropic API key. Optional — without it, Anthropic models are read from the public models.dev / LiteLLM catalogs instead of the live API), OPENAI_API_KEY (OpenAI API key. Optional — falls back to the public catalogs when absent), GOOGLE_API_KEY (Google AI Studio / Gemini API key. Optional), OPENROUTER_API_KEY (OpenRouter key. Optional for discovery (unauthenticated requests are rate-limited), required to execute through OpenRouter), XAI_API_KEY (xAI (Grok) API key. Optional), TYPESAFE_API_KEY (TypeSafe System One (Jev) API key. Optional), KOSHA_CACHE_TTL_HOURS (Override the discovery cache TTL. Defaults to 24 hours).
Account, billing, team, API key and model discovery tools for agents that use ModelsLab.
Which AI model, and what it costs: LiteLLM prices, Arena ratings and price history.
Prices what your coding agents are about to do, before they do it. Plus local cloud and AI cost.
Local profiler: which usage window took you out, and where your agent's money goes
Track AI agent costs, detect waste, optimize models, and prove ROI. 23 MCP tools across 10 domains.
Image and video generation across 40+ providers with your own keys, plus a local asset library.
Provides tools to discover and list servers, agents, and skills in the AI Registry… — 想 7×24 常驻 → 萬星
Fast local and federated OSS code search and repo discovery for AI agents
Answers built from our own checks of this server.