MCP.Market

AIR SDK MCP server

by ArcedeDev·io.github.ArcedeDev/air-sdk·v0.2.12·1 stars
No reviews yet

Collective intelligence for browser automation agents. Site capabilities, selectors, and extraction.

B71/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B71/100

full report

Adoption
New

1 stars58 downloads/wk

Reviews

Write one

Nobody has reviewed AIR SDK yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

AIR SDK tools (4, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • browse_capabilities

    Step 1 of 3: Discover what actions can be automated on a website domain. Returns capabilities (search, login, add to cart, etc.) with confidence scores, execution tiers, selectors, and macro availability. Always follow up with execute_capability (step 2) and report_outcome (step 3).

  • execute_capabilitywrite action

    Step 2 of 3: Get execution guidance for a specific capability. Returns the optimal path: API fast-path, pre-verified macro steps, selector hints, or context for unverified capabilities. Call this after browse_capabilities. After executing with your browser tools, you MUST call report_outcome (step 3) with the CSS selectors you used.

  • extract_url

    Extract structured data from any URL. Returns title, description, content items, metadata, and diagnostics. Handles SPAs (YouTube, Next.js, Nuxt), JSON-LD, and standard meta tags. Costs 1.0 credit (fresh) or 0.1 credit (cached).

  • report_outcome

    REQUIRED: Report the outcome after executing ANY browser action via AIR. This is the final step of every browse \u2192 execute \u2192 report workflow. Without your report, the action you just performed is lost \u2014 no macro gets created, no future agent benefits. Include the CSS selectors you used for each step and whether they worked. Your selectors become verified macros that make future execu

Public scan report

scanner v0.1.10 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan44 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 171 days ago8/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 71/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How AIR SDK compares

Against every graded Scraping and browsing MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
71/100
higher than 36% of 866 Scraping and browsing servers
Tools
4
the typical Scraping and browsing server has 6
Tools that change things
25%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1
more than 50% of 583 Scraping and browsing servers
Downloads a week
58
more than 40% of 309 Scraping and browsing servers with a package

What its tools let an agent do: 3 read · 1 run or deploy

Install AIR SDK in Claude Code, Cursor or VS Code

Runs npx -y @arcede/air-sdk on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add air-sdk -- npx -y @arcede/air-sdk
Add to Cursor

What the publisher says

From the AIR SDK repository's README, as published. We do not edit it. Read it on GitHub

AIR SDK Collective intelligence for agents. Stop your agents from guessing how to use the web. Let them know what to do. Think; hive mind. Let's make the open agent internet.

Install · Quick Start · Why · Agent Skill · Docs

Your browser agent wastes tokens and time every time it asks an LLM what to click. AIR SDK replaces guessing with knowing. This is an early research preview.

Up to 7,000x cost reduction and 280x faster vs frontier models. One function call. Zero code changes.

Benchmarks

Measured across 8 major domains, 40 cold API calls, cache disabled. LLM baseline priced at Frontier Model ($15/$75 per M tokens). AIR SDK at Scale tier ($149/mo, 250K executions).

The more complex the workflow, the more you save. LLM costs compound — every action adds to the conversation context, making each subsequent round trip more expensive. AIR's macro path is always one API call, regardless of how many steps the workflow has.

Methodology & raw data

LLM baseline: Agent inspects page DOM, reasons about which elements to interact with, generates tool calls. Frontier Model pricing ($15/M input, $75/M output).

  • 1 action: ~4,000 input + 800 output tokens x 2 round trips = ~9,600 tokens, ~$0.24, ~4s reasoning time.
  • 10 actions: Context grows with each action (conversation history accumulates). Average ~6,000 input + 1,000 output tokens x 2.5 round trips per action = 25 total LLM calls, ~175,000 tokens, ~$4.13, ~50s reasoning time.
  • Sonnet 4 comparison: 5x cheaper per token — 1 action: ~$0.05, 10 actions: ~$0.83. Still 80–1,400x more expensive than AIR at Scale.

AIR SDK macro path: Pre-verified CSS selectors returned via API. Agent executes directly — no DOM inspection, no LLM reasoning. Cost = plan price / included executions.

Raw API latency (40 measurements, cache disabled):

  • browse_capabilities: 180ms median, 148ms min, 421ms p95
  • execute_capability: 178ms median, 146ms min, 333ms p95
  • Combined: 354ms median, 304ms min, 1010ms p95

Cost per action by tier:

Capabilities discovered: 16 avg per domain (range: 3–39)

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

AIR SDK: common questions

Is AIR SDK MCP server safe?
Mostly: it is graded B (71/100). Read the AIR SDK safety report
How do I install AIR SDK?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does AIR SDK need an API key?
Yes. The registry entry asks for AIR_API_KEY.
Is AIR SDK maintained?
The last commit was 208 days ago (2026-04-10). The latest release is v0.2.12.
What can I use instead of AIR SDK?
Servers from other publishers that do the same job: Unbrowse MCP server, One Search MCP server and Dejo MCP server.
How does AIR SDK compare with other Scraping and browsing MCP servers?
safety score 71/100 (higher than 36% of 866 Scraping and browsing servers); tools 4 (the typical Scraping and browsing server has 6); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to AIR SDK

Same job from other publishers: the closest match first, then the best rated.

  • Unbrowse
    Websites as APIs: read pages, run site tasks via learned APIs, cloud browser with saved logins.
    A
  • One Search
    Web search, URL discovery, scraping & extraction with agent-browser and search providers
    B
  • Dejo
    A browser your AI agent remembers. Learn a site once, replay it in one call, zero model calls.
    A
  • Anakin
    Web data for AI agents: scrape, crawl, search, deep research, site monitoring, browser automation
    B
  • Browser Scraper
    Stealth Chrome for AI agents: bot-protected sites, Turnstile, closed Shadow DOM, clean Markdown.
    A