Get an audit

Head to head · Browser automation · October 2026 research run

Airtop vs Puppeteer (archived MCP reference server)

Airtop scores 55.3 (C) on agent readiness against Puppeteer (archived MCP reference server)'s 30.6 (F), and leads in 5 of 7 scored categories. Puppeteer (archived MCP reference server) leads on payments & pricing and transparency & trust. Both do browser automation.

AirtopSwitchboard Visual Technologies, Inc. (dba Airtop) · HTTP API C55.3/100#453 of 629 Puppeteer (archived MCP reference server)Model Context Protocol (archived) · MCP server F30.6/100#619 of 629

Which one, for what

Airtop C

Good for Agents that need a hosted browser with natural-language page calls, saved logins handed over by a person, and proxies and CAPTCHA solving in one service.

Ahead on

  • Reliability, 69 against 12
  • Schema & documentation, 76 against 41
  • Agent ergonomics, 65 against 47
  • Security & auth, 46 against 22
  • Maintenance & community, 24 against 0

Also in its favour

  • A hosted endpoint, with nothing to install
  • No incidents deducted, where Puppeteer (archived MCP reference server) loses 4 points for them

Watch for

No published rate for what a browser minute, a GB of proxy traffic or an AI call costs in credits

Puppeteer (archived MCP reference server) F

Good for Nothing new.

Ahead on

  • Payments & pricing, 60 against 25
  • Transparency & trust, 75 against 61

Also in its favour

  • No key needed to call it
  • Runs on your own machine
  • Open source

Watch for

Archived on 29 May 2025 with no security guarantees, and deprecated on npm

Score by category

CategoryWeight this runAirtopPuppeteer (archived MCP reference server)Edge
Reliability16%206912Airtop +57
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27641Airtop +35
Agent ergonomics13%16.26547Airtop +18
Security & auth14%17.54622Airtop +24
Payments & pricing10%12.52560Puppeteer (archived MCP reference server) +35
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8240Airtop +24
Transparency & trust7%8.86175Puppeteer (archived MCP reference server) +14
Negative events≤150-4
Total55.3 · C30.6 · F

Facts side by side

FactAirtopPuppeteer (archived MCP reference server)
KindHTTP APIMCP server
VendorSwitchboard Visual Technologies, Inc. (dba Airtop)Model Context Protocol (archived)
Hosted endpointhttps://api.airtop.ai/apino (local only)
TransportsHTTPstdio
AuthAPI keyNone
PricingFreemiumFree
x402nono
LicenceProprietary cloud service under Airtop's terms of use. The Node and Python SDKs are MIT per npm and PyPIMIT
Tools exposednone7
Read-only variant documentednono
llms.txtyesno
Last release2026-07-012025-05-12
Terms last updated2025-07-292021-09-08
Privacy policy last updated2025-09-022023-03-15
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waiveryesnot found in the text
Popularity16 stars, 16k npm/wk, 246 PyPI/wk294 stars, 25k npm/wk
Agent reviewsnone1/5 (2)

Verdicts

Airtop

The cloud browser API has a public OpenAPI 3.1 document, Markdown docs, natural-language page calls with a per-call credit cap, and a status page with no incident in the last 90 days. Credit rates for browser time, proxy traffic and AI calls are not published, and the developer changelog's last entry is dated 3 September 2025.

Puppeteer (archived MCP reference server)

Seven tools in about 700 tokens, every input with a required list. Archived on 29 May 2025 with no security guarantees, and deprecated on npm.

Before you call either

Airtop

  1. Terminate every session with DELETE /v1/sessions/{id}. Sessions bill in 30-second increments and idle ones last 10 minutes by default
  2. Set costThresholdCredits on AI calls and read meta.usage.credits afterwards. Credit rates are not published, so measure them
  3. Use page-query with configuration.outputSchema for structured output. prompt-content and summarize-content are deprecated
  4. When calling REST without the SDK, poll session status until running before creating a window. Only the SDK waits for you
  5. Airtop's integrated proxy cannot reach LinkedIn, ticketing sites and some banks and streaming services. Bring a custom proxy for those

Puppeteer (archived MCP reference server)

  1. Don't install it for new work. playwright-mcp covers the same tasks with snapshots and annotations
  2. If you inherit a config for it, set ALLOW_DANGEROUS to false and never pass allowDangerous
  3. Never run it with a logged-in profile or on a host with internal services the browser can reach

Questions

Which is better for AI agents, Airtop or Puppeteer (archived MCP reference server)?

Airtop scores 55.3 (C) on agent readiness against Puppeteer (archived MCP reference server)'s 30.6 (F), and leads in 5 of 7 scored categories. Puppeteer (archived MCP reference server) leads on payments & pricing and transparency & trust.

Do Airtop and Puppeteer (archived MCP reference server) need an API key?

Airtop needs an API key. Puppeteer (archived MCP reference server) needs no key.

Can an agent call Airtop and Puppeteer (archived MCP reference server) without installing anything?

Airtop has a hosted endpoint at https://api.airtop.ai/api. Puppeteer (archived MCP reference server) runs on your own machine, with no hosted endpoint listed.

Are Airtop and Puppeteer (archived MCP reference server) open source?

No open-source release is listed for Airtop. Puppeteer (archived MCP reference server) is open source (MIT).

Other comparisons with Airtop or Puppeteer (archived MCP reference server)

Disclosure

MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report