Connects your editor to Index9's model directory and OpenRouter for live inference. You get five tools: list_facets for browsing providers and capabilities, find_models for semantic search across 300+ AI models, get_models for bulk metadata retrieval, compare_models for side-by-side diffs of pricing and context windows, and test_model for running live inference or dry-run cost estimates. Requires an OpenRouter API key for actual model calls, but you can explore and compare without one. Useful when you're evaluating models for a project and want to test prompts against multiple providers without leaving your editor or writing integration code.
Discover, shortlist, compare, cost-model, and live-test 300+ AI models from your editor
Per-editor install configs (Cursor, VS Code, Claude Code, Codex): https://index9.dev/#install
npx -y @index9/mcp@latest
Generic MCP client config:
{
"mcpServers": {
"index9": {
"command": "npx",
"args": ["-y", "@index9/mcp@latest"],
"env": {
"OPENROUTER_API_KEY": "sk-or-..."
}
}
}
}
Claude Code one-liner: claude mcp add --transport stdio index9 -- npx -y @index9/mcp.
Required for live test_model calls. Set OPENROUTER_API_KEY in your MCP client config. dryRun=true works without it.
All tool responses include an _index9 object with:
apiBaseUrl: API base URL used for the requestError responses also include:
status: upstream HTTP status code_index9.retryAfterSeconds: present when Retry-After is returned_index9.rateLimit: present when rate-limit headers are returned (x-ratelimit-limit, x-ratelimit-remaining, x-ratelimit-reset)OPENROUTER_API_KEYsecretRequired for live test_model calls. dryRun=true works without it.