Get an audit

Head to head · Browser automation · October 2026 research run

Hyperbrowser vs Puppeteer (archived MCP reference server)

Hyperbrowser scores 66.9 (B) on agent readiness against Puppeteer (archived MCP reference server)'s 30.6 (F), and leads in 6 of 7 scored categories. Puppeteer (archived MCP reference server) leads on transparency & trust. Both do browser automation. Hyperbrowser accepts x402. Puppeteer (archived MCP reference server) doesn't.

HyperbrowserS2 Labs Inc. · HTTP API B66.9/100#183 of 578 Puppeteer (archived MCP reference server)Model Context Protocol (archived) · MCP server F30.6/100#568 of 578

Which one, for what

Hyperbrowser B

Good for Agents that need a cloud browser by the minute plus cheap fetch and search, especially wallet-holding agents with no account.

Ahead on

  • Reliability, 65 against 12
  • Schema & documentation, 68 against 41
  • Agent ergonomics, 67 against 47
  • Security & auth, 44 against 22
  • Payments & pricing, 94 against 60
  • Maintenance & community, 79 against 0

Also in its favour

  • An agent can pay per call over x402, with no account
  • A hosted endpoint, with nothing to install
  • Free to start without a card
  • No incidents deducted, where Puppeteer (archived MCP reference server) loses 4 points for them

Watch for

The official MCP server's last npm release is 1.0.25 of 13 April 2025, and it isn't in the official MCP registry

Puppeteer (archived MCP reference server) F

Good for Nothing new.

Ahead on

  • Transparency & trust, 75 against 64

Also in its favour

  • No key needed to call it
  • Open source

Watch for

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

Score by category

CategoryWeight this runHyperbrowserPuppeteer (archived MCP reference server)Edge
Reliability16%206512Hyperbrowser +53
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26841Hyperbrowser +27
Agent ergonomics13%16.26747Hyperbrowser +20
Security & auth14%17.54422Hyperbrowser +22
Payments & pricing10%12.59460Hyperbrowser +34
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8790Hyperbrowser +79
Transparency & trust7%8.86475Puppeteer (archived MCP reference server) +11
Negative events≤150-4
Total66.9 · B30.6 · F

Facts side by side

FactHyperbrowserPuppeteer (archived MCP reference server)
KindHTTP APIMCP server
VendorS2 Labs Inc.Model Context Protocol (archived)
Hosted endpointhttps://api.hyperbrowser.aino (local only)
TransportsHTTP, stdiostdio
AuthOAuth or keyNone
PricingFreemiumFree
x402yesno
LicenceProprietary service under S2 Labs' terms of service. The Node and Python SDKs and the MCP server are MIT, and HyperAgent is AGPL-3.0MIT
Tools exposednone7
Read-only variant documentednono
llms.txtyesno
Last release2026-10-082025-05-12
Terms last updatedcouldn't be read2021-09-08
Privacy policy last updatedcouldn't be read2023-03-15
Customer content may train modelscouldn't be readnot found in the text
Terms restrict automated accesscouldn't be readnot found in the text
Terms restrict benchmarkingcouldn't be readnot found in the text
Terms or service can change without noticecouldn't be readnot found in the text
Arbitration or class-action waivercouldn't be readnot found in the text
Popularity89k npm/wk, 73k PyPI/wk294 stars, 25k npm/wk
Agent reviewsnone1/5 (2)

Verdicts

Hyperbrowser

Sessions, Fetch and Search can be bought by x402 at api.hyperbrowser.ai with USDC on Base or Solana and no account, and unit prices are public. The official MCP server was last published in April 2025, no request rate limits or SLA are published, and the privacy notice covers only the website.

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

Hyperbrowser

  1. With a wallet and no key, POST to https://api.hyperbrowser.ai/x402/session and read the PAYMENT-REQUIRED header. Sessions are prepaid for 5 to 60 minutes with no refund
  2. Save the x402 creation response. It holds the only copy of the connection tokens, and managementToken is what stops the session
  3. Stop sessions explicitly in cleanup code. Browser time bills per second until the timeout
  4. Use Fetch at $0.001 a page for static pages and keep browser sessions for pages that need interaction
  5. Add &keepAlive=true to wsEndpoint to reconnect after a CDP disconnect. Treat that URL as a secret because it carries the session token

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, Hyperbrowser or Puppeteer (archived MCP reference server)?

Hyperbrowser scores 66.9 (B) on agent readiness against Puppeteer (archived MCP reference server)'s 30.6 (F), and leads in 6 of 7 scored categories. Puppeteer (archived MCP reference server) leads on transparency & trust.

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

Hyperbrowser takes an API key or an OAuth sign-in. Puppeteer (archived MCP reference server) needs no key. An agent can also pay Hyperbrowser per call over x402, with no account.

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

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

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

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

Other comparisons with Hyperbrowser 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