Kosha Model Discovery MCP Server
io.github.sriinnu/kosha-discovery
What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the Kosha Model Discovery MCP server?
Tells your agent which model to use and what it costs, across 45 providers and local runtimes.
How to install Kosha Model Discovery
Copy-paste configuration for popular MCP clients.
ANTHROPIC_API_KEYsecretAnthropic API key. Optional — without it, Anthropic models are read from the public models.dev / LiteLLM catalogs instead of the live API.
OPENAI_API_KEYsecretOpenAI API key. Optional — falls back to the public catalogs when absent.
GOOGLE_API_KEYsecretGoogle AI Studio / Gemini API key. Optional.
OPENROUTER_API_KEYsecretOpenRouter key. Optional for discovery (unauthenticated requests are rate-limited), required to execute through OpenRouter.
XAI_API_KEYsecretxAI (Grok) API key. Optional.
TYPESAFE_API_KEYsecretTypeSafe System One (Jev) API key. Optional.
KOSHA_CACHE_TTL_HOURSOverride the discovery cache TTL. Defaults to 24 hours.
{
"mcpServers": {
"kosha-discovery": {
"command": "npx",
"args": [
"-y",
"@sriinnu/kosha-discovery"
],
"env": {
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"GOOGLE_API_KEY": "<YOUR_GOOGLE_API_KEY>",
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>",
"XAI_API_KEY": "<YOUR_XAI_API_KEY>",
"TYPESAFE_API_KEY": "<YOUR_TYPESAFE_API_KEY>",
"KOSHA_CACHE_TTL_HOURS": "<YOUR_KOSHA_CACHE_TTL_HOURS>"
}
}
}
}Related MCP servers

Tokens and cost for Claude Code, Codex and 14 more AI coding agents, from local session files.

Hive Capital
HiveCapital MCP Server — autonomous investment layer for AI agents

Hive Compute
HiveCompute MCP Server — decentralized inference router for AI agents

Biolab MCP Server
Auditable MCP server for PubMed, Europe PMC, ClinicalTrials.gov, and bioRxiv/medRxiv queries
Unified MCP for Scrimba's interactive programming education with visual learning