MCP Integration

Connect any AI client that supports the Model Context Protocol (MCP) to this registry.

Endpoint

POST https://your-mcp-app.vercel.app/api/mcp

If MCP_API_KEY is configured, pass it as a Bearer token in the Authorization header.

Available Tools

list_models

List all models in the registry

{ limit?: number, offset?: number, provider?: string }

resolve_model

Resolve an alias or ID to its canonical form

{ input: string }

get_default_model

Get the default recommended model

{}

get_sync_status

Get the current sync status

{}

Claude Desktop Configuration

Add this to your Claude Desktop MCP configuration:

{
  "mcpServers": {
    "openrouter-registry": {
      "url": "https://your-mcp-app.vercel.app/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Usage Examples

Resolve a model alias in your agent:

// In your agent/assistant:
const result = await mcp.callTool('resolve_model', { input: 'sonnet' });
// → { resolved: 'anthropic/claude-sonnet-4-5', source: 'alias', found: true }

Get the default model:

const result = await mcp.callTool('get_default_model', {});
// → { resolved: 'anthropic/claude-sonnet-4-5', ... }

Cron Sync

The registry is automatically refreshed weekly via Vercel Cron:

// vercel.json
{
  "crons": [
    {
      "path": "/api/cron/sync",
      "schedule": "0 0 * * 0"
    }
  ]
}