Kosha Model Discovery

Tells your agent which model to use and what it costs, across 46 providers and local runtimes.

What does this entry provide?

Kosha Model Discovery is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 78/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding Kosha Model Discovery to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.

Snapshot facts

Source: Official MCP Registry
Quality: 78/100
Install method: npm
Repo: sriinnu/kosha-discovery
Repo updated: Oct 6, 2026

Install command

npx -y @sriinnu/kosha-discovery@1.8.1

Install method: npm

Review the upstream source before running this command.

GitHub project

Quality

Repo stars

Repo updated

Oct 6, 2026

How is this score calculated?

Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.

MCP manifest

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-10-06T14:23:23.546481Z",
      "publishedAt": "2026-10-06T14:23:23.546481Z",
      "statusChangedAt": "2026-10-06T14:23:23.546481Z"
    }
  },
  "server": {
    "name": "io.github.sriinnu/kosha-discovery",
    "_meta": {
      "io.modelcontextprotocol.registry/publisher-provided": {
        "tool": "manual",
        "notes": "Every provider key is optional. With no credentials at all, kosha still answers from the public models.dev and LiteLLM catalogs plus a curated offline list, so the server is useful on a fresh machine. Full env var reference: docs/credentials.md."
      }
    },
    "title": "Kosha Model Discovery",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "version": "1.8.1",
    "packages": [
      {
        "version": "1.8.1",
        "transport": {
          "type": "stdio"
        },
        "identifier": "@sriinnu/kosha-discovery",
        "registryType": "npm",
        "registryBaseUrl": "https://registry.npmjs.org",
        "environmentVariables": [
          {
            "name": "ANTHROPIC_API_KEY",
            "isSecret": true,
            "description": "Anthropic API key. Optional — without it, Anthropic models are read from the public models.dev / LiteLLM catalogs instead of the live API."
          },
          {
            "name": "OPENAI_API_KEY",
            "isSecret": true,
            "description": "OpenAI API key. Optional — falls back to the public catalogs when absent."
          },
          {
            "name": "GOOGLE_API_KEY",
            "isSecret": true,
            "description": "Google AI Studio / Gemini API key. Optional."
          },
          {
            "name": "OPENROUTER_API_KEY",
            "isSecret": true,
            "description": "OpenRouter key. Optional for discovery (unauthenticated requests are rate-limited), required to execute through OpenRouter."
          },
          {
            "name": "XAI_API_KEY",
            "isSecret": true,
            "description": "xAI (Grok) API key. Optional."
          },
          {
            "name": "TYPESAFE_API_KEY",
            "isSecret": true,
            "description": "TypeSafe System One (Jev) API key. Optional."
          },
          {
            "name": "KOSHA_CACHE_TTL_HOURS",
            "description": "Override the discovery cache TTL. Defaults to 24 hours."
          }
        ]
      }
    ],
    "repository": {
      "url": "https://github.com/sriinnu/kosha-discovery",
      "source": "github"
    },
    "websiteUrl": "https://github.com/sriinnu/kosha-discovery",
    "description": "Tells your agent which model to use and what it costs, across 46 providers and local runtimes."
  }
}

Report an issue with this listing