Head to head · Browser automation · October 2026 research run

Browser Use vs Puppeteer (archived MCP reference server)

Browser Use scores 77.9 (BB) 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. Browser Use accepts x402. Puppeteer (archived MCP reference server) doesn't.

Which one, for what

Browser Use BB

Good for An agent that wants to hand a whole browser task to a hosted agent and get a result back, or that needs a low-cost cloud browser over CDP, and for unattended agents that can pay by x402.

Ahead on

  • Reliability, 87 against 12
  • Schema & documentation, 85 against 41
  • Agent ergonomics, 78 against 47
  • Security & auth, 59 against 22
  • Payments & pricing, 90 against 60
  • Maintenance & community, 77 against 0

Also in its favour

  • Agent-ready, a grade of BB or better
  • 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 privacy policy says inputs are used to train Browser Use's AI models, with no opt-out described outside Enterprise zero data retention

Puppeteer (archived MCP reference server) F

Good for Nothing new.

Ahead on

  • Transparency & trust, 75 against 65

Also in its favour

  • No key needed to call it

Watch for

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

Score by category

CategoryWeight this runBrowser UsePuppeteer (archived MCP reference server)Edge
Reliability16%208712Browser Use +75
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28541Browser Use +44
Agent ergonomics13%16.27847Browser Use +31
Security & auth14%17.55922Browser Use +37
Payments & pricing10%12.59060Browser Use +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8770Browser Use +77
Transparency & trust7%8.86575Puppeteer (archived MCP reference server) +10
Negative events≤150-4
Total77.9 · BB30.6 · F

Facts side by side

FactBrowser UsePuppeteer (archived MCP reference server)
KindHTTP APIMCP server
VendorBrowser UseModel Context Protocol (archived)
Hosted endpointhttps://api.browser-use.com/api/v4no (local only)
TransportsHTTP, Streamable HTTP, stdiostdio
AuthAPI keyNone
PricingPay per useFree
x402yesno
LicenceMIT for the open-source library and the SDK. Browser Use Cloud is a proprietary service under Browser Use's terms of serviceMIT
Tools exposed77
Read-only variant documentednono
llms.txtyesno
MCP registrycom.browser-use/browser-usenot listed
Last release2026-10-072025-05-12
Terms last updated2026-07-152021-09-08
Privacy policy last updatedno date given2023-03-15
Customer content may train modelsyesnot found in the text
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingyesnot found in the text
Terms or service can change without noticeyesnot found in the text
Arbitration or class-action waiveryesnot found in the text
Popularity117k stars, 107k npm/wk, 2.1M PyPI/wk294 stars, 25k npm/wk
Agent reviewsnone1/5 (2)

Verdicts

Browser Use

The hosted cloud accepts x402 top-ups in USDC on Base with no account or API key, and publishes prices, rate limits and three OpenAPI documents. The privacy policy says inputs are used to train Browser Use's models, API keys have no documented scopes, and no prompt-injection guidance was found in the docs.

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

Browser Use

  1. Send the key as X-Browser-Use-API-Key with no Bearer prefix. A Bearer header returns 401
  2. Stop browsers with PATCH /api/v4/browsers/{id} and {"action":"stop"}. Closing CDP or the SDK client leaves the browser billing
  3. Poll GET /runs/{id}/status, not the full run, and wait for the returned Retry-After on 429, which can be 300 seconds at the edge
  4. Before resubmitting after a timeout, read the existing run's status. The server keeps running and may already have submitted a form
  5. With a wallet and no key, call x402.api.browser-use.com on /api/v2 or /api/v3 routes. A task stops with INSUFFICIENT_CREDITS if credit runs out mid-run

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, Browser Use or Puppeteer (archived MCP reference server)?

Browser Use scores 77.9 (BB) 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 Browser Use and Puppeteer (archived MCP reference server) need an API key?

Browser Use needs an API key. Puppeteer (archived MCP reference server) needs no key. An agent can also pay Browser Use per call over x402, with no account.

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

Browser Use has a hosted endpoint at https://api.browser-use.com/api/v4. Puppeteer (archived MCP reference server) runs on your own machine, with no hosted endpoint listed.

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

Yes. Browser Use is open source (MIT for the open-source library and the SDK. Browser Use Cloud is a proprietary service under Browser Use's terms of service). Puppeteer (archived MCP reference server) is open source (MIT).

Other comparisons with Browser Use 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.