About auxiliar-mcp
auxiliar-mcp helps AI agents discover web search, scraping, browser, and related providers through measured public benchmarks. Its recommendations include dated scorecards, caveats, and executable gateway call patterns.
Key features
- 01Provider recommendations by task
- 02Rankings by quality, latency, cost, and errors
- 03Dated scorecards with raw metrics
- 04Provider details, pricing, and guidance
- 05Executable gateway call patterns
Use cases
- 01Choose a provider for a web search task
- 02Compare scraping providers using benchmark results
- 03Check latency or cost constraints before routing
MCP support
The MCP server exposes tools to recommend providers and retrieve scorecards, provider details, and gateway information. It currently supports tool discovery; provider execution through this MCP is listed as a roadmap item.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
4Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| job | enum | Yes | The job to be done. search = Web search: query → ranked results | scrape = One URL → clean page content/markdown, anti-bot handled | crawl = Site → enumerate and fetch many pages | extract_ai = Page → structured fields from an AI/natural-language schema | extract_rules = Page → structured fields via CSS/XPath rules | answer = Question → synthesized answer with cited sources | screenshot = URL → rendered page image | scrape_domain = Domain-specific scrapers for hard targets (e-commerce, social) | act = Declarative page interactions (click, fill, scroll) in one call | act_agent = Autonomous natural-language browser agent for multi-step goals | serp = Google SERP verticals (web, news, images, places, scholar) as structured JSON | parse = PDF/document → text (OCR where supported) | watch = URL → change detection / monitoringsearch | scrape | crawl | extract_ai | extract_rules | answer | screenshot | scrape_domain | act | act_agent | serp | parse | watch |
| limit | integer | No | Max candidates to return. Default 3. |
| max_cost_usd | number | No | Exclude providers whose measured cost per call/success exceeds this (USD). |
| optimize_for | enum | No | Ranking priority. balanced/quality = published composite; cost/latency = that measured metric. Default balanced.balanced | quality | cost | latency |
| max_latency_ms | number | No | Exclude providers whose measured latency p50 exceeds this. |
Details
From the project READMEauxiliar-mcp
Eval-backed tool discovery for AI agents, on the 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.
Ask 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.
Install
claude mcp add auxiliar -- npx auxiliar-mcp
or in any MCP client config:
{ "mcpServers": { "auxiliar": { "command": "npx", "args": ["auxiliar-mcp"] } } }
Tools
| Tool | What it does |
|---|---|
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. |
get_scorecard | The full leaderboard for one verb — every scored provider, raw metrics, run dates. |
get_provider | One provider in full: route, pricing, choose/avoid guidance, all its dated scorecards. |
about_auxiliar | What the gateway is, how to get a key, how to call it. |
Every 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.
Recommendations return an executable call pattern:
https://api.auxiliar.ai/{provider}/{provider-native-path}
Authorization: Bearer <your auxiliar API key>
Same 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.
Where the data comes from
Benchmark data loads at runtime from 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. 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.
Development
npm install
npm run build # tsc → dist/ (+ bundled data snapshot)
npm test # unit tests + end-to-end stdio round-trip
npm run update-fallback # refresh src/data/evals-fallback.json from production
Releasing: 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.
Roadmap
- v0.23 (this release) — eval-backed discovery.
- 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.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.