{
  "markdown": "# @index9/mcp\n\nDiscover, shortlist, compare, cost-model, and live-test 300+ AI models from your editor\n\n> Per-editor install configs (Cursor, VS Code, Claude Code, Codex): https://index9.dev/#install\n\n## Install\n\n```bash\nnpx -y @index9/mcp@latest\n```\n\nGeneric MCP client config:\n\n```json\n{\n  \"mcpServers\": {\n    \"index9\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@index9/mcp@latest\"],\n      \"env\": {\n        \"OPENROUTER_API_KEY\": \"sk-or-...\"\n      }\n    }\n  }\n}\n```\n\nClaude Code one-liner: `claude mcp add --transport stdio index9 -- npx -y @index9/mcp`.\n\n## OpenRouter API key\n\nRequired for live test_model calls. Set OPENROUTER_API_KEY in your MCP client config. dryRun=true works without it.\n\n## Tools\n\n- **list_facets**: List available providers, capabilities, modalities, and tokenizers\n- **find_models**: Search AI models by semantic query or filters\n- **get_models**: Fetch full model metadata for up to 100 IDs or aliases\n- **compare_models**: Diff 2-10 models across pricing, context, capabilities, and tokenizer\n- **test_model**: Run live inference or dry-run cost estimates on 1-10 models (requires OpenRouter API key)\n\n## Response metadata\n\nAll tool responses include an `_index9` object with:\n\n- `apiBaseUrl`: API base URL used for the request\n\nError responses also include:\n\n- `status`: upstream HTTP status code\n- `_index9.retryAfterSeconds`: present when `Retry-After` is returned\n- `_index9.rateLimit`: present when rate-limit headers are returned (`x-ratelimit-limit`, `x-ratelimit-remaining`, `x-ratelimit-reset`)\n",
  "bytes": 1540,
  "sha": "488d5b0092e35d496b38cec7d04ae686d340ffa07f4b8e4163d858cc22826cd4",
  "repo_slug": "index9-org/mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_index9_org_mcp_c0074035/readme"
}