PluginBench
MCP Server
Active
MIT

Kosha Model Discovery MCP Server

io.github.sriinnu/kosha-discovery

RepositoryRegistry
How to choose

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.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • ANTHROPIC_API_KEY
    secret

    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
    secret

    OpenAI API key. Optional — falls back to the public catalogs when absent.

  • GOOGLE_API_KEY
    secret

    Google AI Studio / Gemini API key. Optional.

  • OPENROUTER_API_KEY
    secret

    OpenRouter key. Optional for discovery (unauthenticated requests are rate-limited), required to execute through OpenRouter.

  • XAI_API_KEY
    secret

    xAI (Grok) API key. Optional.

  • TYPESAFE_API_KEY
    secret

    TypeSafe System One (Jev) API key. Optional.

  • KOSHA_CACHE_TTL_HOURS

    Override the discovery cache TTL. Defaults to 24 hours.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "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.

0
TypeScript
AGPL-3.0
View repository →
HIHive Capital logo

Hive Capital

Maintained

HiveCapital MCP Server — autonomous investment layer for AI agents

0
JavaScript
MIT
View repository →
HIHive Compute logo

Hive Compute

Maintained

HiveCompute MCP Server — decentralized inference router for AI agents

0
JavaScript
MIT
View repository →
HIHive Connector logo

Hive Connector

Maintained

MCP server for Hive Civilization

0
JavaScript
MIT
View repository →

Auditable MCP server for PubMed, Europe PMC, ClinicalTrials.gov, and bioRxiv/medRxiv queries

1
Python
MIT
View repository →

Unified MCP for Scrimba's interactive programming education with visual learning