Models MCP

Search, compare, and inspect AI models by pricing, context window, and capabilities. An MCP server over the models.dev catalog (models.dev/api.json), so your agent always has current model data without you hand-maintaining a list.

models.dev itself doesn't ship an MCP server, just a JSON API and a TypeScript SDK for reading it. This fills that gap.

Runs two ways from the same tool code:

• stdio (src/index.ts) for local MCP clients

• Cloudflare Worker (src/worker.ts) as a remote Streamable HTTP endpoint at /mcp

Tools

Install

npm install
npm run build

Run standalone over stdio (for testing)

npm start

It speaks MCP over stdio, so you won't see much directly; use the MCP Inspector to poke at it:

npx @modelcontextprotocol/inspector node dist/index.js

Host on Cloudflare Workers

The Worker entry (src/worker.ts) serves the same tools over Streamable HTTP at /mcp, with:

• Catalog caching in the Workers Cache API (caches.default) with a 1-hour TTL, shared across requests and isolates.

• Per-IP rate limiting via a Workers rate limiting binding: 60 requests/minute per IP, enforced per Cloudflare location. Excess requests get 429 with Retry-After: 60.

# local dev at http://localhost:8787/mcp
npm run dev:worker

# deploy
npm run deploy

After deploy, your endpoint is https://models-mcp.<your-subdomain>.workers.dev/mcp.

Point MCP clients at it:

Claude Code:

claude mcp add --transport http models-mcp https://models-mcp.<your-subdomain>.workers.dev/mcp

Generic client config (anything that speaks Streamable HTTP):

{
  "mcpServers": {
    "models-mcp": {
      "url": "https://models-mcp.<your-subdomain>.workers.dev/mcp"
    }
  }
}

For stdio-only clients (Claude Desktop), bridge with mcp-remote:

{
  "mcpServers": {
    "models-mcp": {
      "command": "npx",
      "args": ["mcp-remote", "https://models-mcp.<your-subdomain>.workers.dev/mcp"]
    }
  }
}

No API keys required anywhere. All data comes from the public models.dev/api.json endpoint.

Tests

npm test

Covers the catalog client (flattening, TTL caching, force refresh, stale-on-failure fallback, id resolution) and all five tools end-to-end through a real MCP client session over an in-memory transport.

Notes on the data

• The catalog is cached for 1 hour: in the Workers Cache API when hosted, in process memory over stdio. Call refresh_catalog to force an update. If a refetch fails, the last good catalog keeps being served.

• models.dev doesn't publish a versioned schema for consumers, so the types in src/types.ts are intentionally loose (index signatures preserve any fields not explicitly typed).

• Model ids follow the provider/model convention used by the AI SDK and OpenCode, e.g. anthropic/claude-sonnet-4-5. get_model and compare_models also accept a bare model id if it's unambiguous across providers.

Possible extensions

• A list_facets tool (modalities, tokenizers) similar to what other model-catalog MCPs expose.

• A test_model tool that makes a live call through whichever provider key you have configured, for latency/cost sanity checks.

• OAuth or Cloudflare Access in front of the Worker, if you want it private.