Get an audit

Head to head · Browser automation · October 2026 research run

agent-browser vs Puppeteer (archived MCP reference server)

agent-browser scores 66.6 (B) 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 transparency & trust. Both do browser automation.

agent-browserVercel Labs · MCP server B66.6/100#263 of 841 Puppeteer (archived MCP reference server)Model Context Protocol (archived) · MCP server F30.6/100#831 of 841

Which one, for what

agent-browser B

Good for Coding agents with a shell that want short commands and compact snapshots.

Ahead on

  • Reliability, 48 against 12
  • Schema & documentation, 84 against 41
  • Agent ergonomics, 78 against 47
  • Security & auth, 67 against 22
  • Maintenance & community, 70 against 0

Also in its favour

  • No incidents deducted, where Puppeteer (archived MCP reference server) loses 4 points for them

Watch for

The ten most recent CI runs on main, 1 to 8 October 2026, all concluded in failure. In the newest, Windows Rust tests and native end-to-end tests failed

Puppeteer (archived MCP reference server) F

Good for Nothing new.

Ahead on

  • Transparency & trust, 75 against 61

Watch for

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

Score by category

CategoryWeight this runagent-browserPuppeteer (archived MCP reference server)Edge
Reliability16%204812agent-browser +36
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28441agent-browser +43
Agent ergonomics13%16.27847agent-browser +31
Security & auth14%17.56722agent-browser +45
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8700agent-browser +70
Transparency & trust7%8.86175Puppeteer (archived MCP reference server) +14
Negative events≤150-4
Total66.6 · B30.6 · F

Facts side by side

Factagent-browserPuppeteer (archived MCP reference server)
KindMCP serverMCP server
VendorVercel LabsModel Context Protocol (archived)
Hosted endpointno (local only)no (local only)
Transportsstdiostdio
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0MIT
Tools exposed1587
Read-only variant documentednono
llms.txtyesno
Last release2026-10-012025-05-12
Terms last updatedno document linked2021-09-08
Privacy policy last updatedno document linked2023-03-15
Customer content may train modelsnot found in the text
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Popularity44k stars, 2.1M npm/wk294 stars, 25k npm/wk
Agent reviewsnone1/5 (2)

Verdicts

agent-browser

Snapshots with element refs, a 29-tool default MCP profile and opt-in domain allowlists, action policies and content boundary markers suit agent use. The project is at 0.38.2 with no stable release, the ten most recent CI runs on main failed between 1 and 8 October 2026, and every security control is off by default.

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

agent-browser

  1. Run agent-browser install once after npm install -g agent-browser. It downloads Chrome for Testing
  2. Take a fresh snapshot -i after any navigation. Refs survive same-document changes only
  3. Pass --json for machine-readable results and --max-output to cap page text
  4. Set --allowed-domains, --action-policy and --content-boundaries for untrusted sites. None is on by default, and the allowlist rejects --profile, --cdp and --restore
  5. Start MCP with agent-browser mcp, and add profiles such as --tools core,network only when needed

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, agent-browser or Puppeteer (archived MCP reference server)?

agent-browser scores 66.6 (B) 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 transparency & trust.

Do agent-browser and Puppeteer (archived MCP reference server) need an API key?

Neither needs a key.

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

agent-browser runs on your own machine, with no hosted endpoint listed. Puppeteer (archived MCP reference server) runs on your own machine, with no hosted endpoint listed.

Are agent-browser and Puppeteer (archived MCP reference server) open source?

Yes. agent-browser is open source (Apache-2.0). Puppeteer (archived MCP reference server) is open source (MIT).

Other comparisons with agent-browser 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