{
  "markdown": "# auxiliar-mcp\n\nEval-backed tool discovery for AI agents, on the [auxiliar.ai](https://auxiliar.ai) web-access gateway — one API key for 24 search, scraping, browser-automation and voice APIs, upstream keys injected server-side, usage at each provider's real metered price.\n\nAsk it *\"what's the best provider for this job?\"* and it answers from **measured public benchmarks** — every provider runs the identical task corpus per verb; scorecards carry their run dates; weak scores are published, not hidden.\n\n## Install\n\n```bash\nclaude mcp add auxiliar -- npx auxiliar-mcp\n```\n\nor in any MCP client config:\n\n```json\n{ \"mcpServers\": { \"auxiliar\": { \"command\": \"npx\", \"args\": [\"auxiliar-mcp\"] } } }\n```\n\n## Tools\n\n| Tool | What it does |\n|---|---|\n| `recommend_tools` | Best provider(s) for a job (`search`, `scrape`, `crawl`, `extract_ai`, `extract_rules`, `answer`, `screenshot`, `scrape_domain`, `act`, `act_agent`, `serp`, `parse`, `watch`), ranked by measured quality/latency/cost/errors. Optional `optimize_for`, `max_latency_ms`, `max_cost_usd`, `limit`. |\n| `get_scorecard` | The full leaderboard for one verb — every scored provider, raw metrics, run dates. |\n| `get_provider` | One provider in full: route, pricing, choose/avoid guidance, all its dated scorecards. |\n| `about_auxiliar` | What the gateway is, how to get a key, how to call it. |\n\nEvery response carries the run date behind each number (`measured_on`, `latest_run`), the ranking context (`rank #n of m`), honest `caveats`, providers `excluded_by_constraints` (never silently dropped), and `gated_not_scored` entries for providers that couldn't be scored on the shared corpora.\n\nRecommendations return an executable call pattern:\n\n```\nhttps://api.auxiliar.ai/{provider}/{provider-native-path}\nAuthorization: Bearer <your auxiliar API key>\n```\n\nSame paths, parameters and responses as each provider's own docs — the gateway injects the upstream key server-side. Get a key (with $5 free credit, no card) at [auxiliar.ai](https://auxiliar.ai).\n\n## Where the data comes from\n\nBenchmark data loads at runtime from [`auxiliar.ai/evals.json`](https://auxiliar.ai/evals.json) (1h in-memory cache) and falls back to a bundled snapshot offline — responses declare which via `data_source`. The same data renders the human-readable scorecards at [auxiliar.ai/tools](https://auxiliar.ai/tools/). Rankings carry no house incentive: the gateway's fee is flat at credit top-up, so nothing is earned by steering you toward pricier providers.\n\n## Development\n\n```bash\nnpm install\nnpm run build         # tsc → dist/ (+ bundled data snapshot)\nnpm test              # unit tests + end-to-end stdio round-trip\nnpm run update-fallback  # refresh src/data/evals-fallback.json from production\n```\n\nReleasing: bump the version in `package.json` and `server.json` (two spots) — `npm run check-versions` (run automatically at prepublish) enforces sync — then `npm publish` and `mcp-publisher publish`.\n\n## Roadmap\n\n- **v0.23 (this release)** — eval-backed discovery.\n- **v1.0** — in-loop execution: call the providers through the gateway from this MCP (`web_search`, `scrape`, `extract`, `crawl`, …), routed by the same measured rankings.\n\n## License\n\nMIT\n",
  "bytes": 3200,
  "sha": "466d4f090896b840fc7b2726c69946cda47d05b69cca720d24ce814be814cb3d",
  "repo_slug": "auxiliar-ai/auxiliar-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_auxiliar_ai_auxiliar_mcp_941ab851/readme"
}