Auxiliar Mcp

io.github.auxiliar-aiPublished by GitHub account auxiliar-aiv0.23.0Updated Nov 3, 2026

Eval-backed discovery for the auxiliar.ai gateway — the best web-access provider per job, measured.

VerifiedSTDIODesktop onlyWeb Search & ScrapingData & Analytics

Overview

AI-generated overview

Local stdio MCP server that recommends the best web-access provider (search, scraping, browser automation, voice) for a job, using measured benchmark…

What you can do
  • Recommend ranked providers for a job verb such as search, scrape, crawl, extract, screenshot or act, with optional quality, latency and cost constraints
  • Show the full leaderboard for one verb with raw metrics and run dates
  • Describe a single provider in full: route, pricing, choose/avoid guidance and dated scorecards
  • Explain the auxiliar.ai gateway, how to get a key and how to call it
  • Return an executable call pattern for the recommended provider
When to use it
Useful when an assistant has to pick among many web-access APIs and you want the choice backed by published, dated benchmark data rather than guesswork, or when you plan to route web tasks through the auxiliar.ai gateway.
Requirements
Runs locally via npx (Node.js). No environment variables or headers are declared. Benchmark data is fetched at runtime from auxiliar.ai with a bundled offline fallback. Actually calling the recommended providers requires an auxiliar.ai API key, obtained separately.
Before you install
The server itself declares no credentials, but the call patterns it returns use an auxiliar.ai API key as a bearer token, and usage is billed at each provider's metered price against gateway credit. Recommendations point to a specific commercial gateway. Benchmark data is loaded from a remote file at runtime, so rankings depend on that source.

Installation

In SourceWeft

  1. Open Auxiliar Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

auxiliar-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

bash
claude mcp add auxiliar -- npx auxiliar-mcp

or in any MCP client config:

json
{ "mcpServers": { "auxiliar": { "command": "npx", "args": ["auxiliar-mcp"] } } }

Tools

ToolWhat it does
recommend_toolsBest 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_scorecardThe full leaderboard for one verb — every scored provider, raw metrics, run dates.
get_providerOne provider in full: route, pricing, choose/avoid guidance, all its dated scorecards.
about_auxiliarWhat 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

bash
npm installnpm run build         # tsc → dist/ (+ bundled data snapshot)npm test              # unit tests + end-to-end stdio round-tripnpm 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

Source: README.md at commit 42cdcaa

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.23.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts