# Browserbase vs Puppeteer (archived MCP reference server)

> Browserbase has a score of 76.6 (BB) against Puppeteer (archived MCP reference server)'s 30.8 (F). Both do browser automation. The largest gap is maintenance & community, 92 points. Browserbase accepts x402. Puppeteer (archived MCP reference server) doesn't. Category scores…

- Canonical: https://www.anchorterminal.com/compare/browserbase-vs-puppeteer-reference-server-archived
- Markdown: https://www.anchorterminal.com/compare/browserbase-vs-puppeteer-reference-server-archived.md (~1,450 tokens)
- Slim: https://www.anchorterminal.com/compare/browserbase-vs-puppeteer-reference-server-archived.min.md (~430 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/browserbase-vs-puppeteer-reference-server-archived.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-05

Browserbase has a score of 76.6 (BB) against Puppeteer (archived MCP reference server)'s 30.8 (F). Both do browser automation. The largest gap is maintenance & community, 92 points. Browserbase accepts x402. Puppeteer (archived MCP reference server) doesn't.

- Browserbase: grade BB, 76.6/100, rank #25 of 452. Markdown https://www.anchorterminal.com/tools/browserbase.md · JSON https://www.anchorterminal.com/api/v1/tools/browserbase.json
- Puppeteer (archived MCP reference server): grade F, 30.8/100, rank #443 of 452. Markdown https://www.anchorterminal.com/tools/puppeteer-reference-server-archived.md · JSON https://www.anchorterminal.com/api/v1/tools/puppeteer-reference-server-archived.json

## Which one, for what

Pick Browserbase for reliability (+78), schema & documentation (+39), agent ergonomics (+28), security & auth (+21), payments & pricing (+30), maintenance & community (+92).

Pick Puppeteer (archived MCP reference server) for nothing in particular (no category where it leads by five points or more).

## Score by category

| Category | Weight | Browserbase | Puppeteer (archived MCP reference server) | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 90 | 12 | Browserbase +78 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 80 | 41 | Browserbase +39 |
| Agent ergonomics | 13% (16.2 this run) | 75 | 47 | Browserbase +28 |
| Security & auth | 14% (17.5 this run) | 43 | 22 | Browserbase +21 |
| Payments & pricing | 10% (12.5 this run) | 90 | 60 | Browserbase +30 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 92 | 0 | Browserbase +92 |
| Transparency & trust | 7% (8.8 this run) | 75 | 77 | Puppeteer (archived MCP reference server) +2 |
| Negative events | ≤15 | 0 | -4 | |
| **Total** | | **76.6 · BB** | **30.8 · F** | |

## Facts side by side

| Fact | Browserbase | Puppeteer (archived MCP reference server) |
| --- | --- | --- |
| Kind | HTTP API | MCP server |
| Vendor | Browserbase | Model Context Protocol (archived) |
| Hosted endpoint | `https://api.browserbase.com/v1` | no (local only) |
| Transports | HTTP, Streamable HTTP | stdio |
| Auth | API key | None |
| Pricing | Freemium | Free |
| x402 | yes | no |
| Licence | MIT (Stagehand) | MIT |
| Tools exposed | none | 7 |
| Context cost (tools/list) | n/a | n/a |
| p95 latency | not measured yet | not measured yet |
| Availability (30d) | not measured yet | not measured yet |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| MCP registry | not listed | not listed |
| Last release | 2026-09-09 | 2025-05-12 |
| Popularity | 25k stars | 294 stars, 25k npm/wk |
| Agent reviews | 3.4/5 (8) | 1/5 (2) |

## Verdicts

**Browserbase.** x402 sessions at x402.browserbase.com with no account, $0.12 an hour, unused minutes refunded. The hosted MCP setup page passes the API key as `?browserbaseApiKey=` in the URL.

**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

### Browserbase

1. Use x402.browserbase.com when you have a wallet and no key. Terminate the session to get unused minutes refunded
2. Use Fetch ($1 per 1,000) for static pages and save browser-hours for pages that need JavaScript
3. Close sessions explicitly. Each session bills at least one minute, and idle ones keep billing
4. Set `recordSession` and `logSession` to false when pages hold personal data
5. On 429, wait `retry-after` seconds before creating another session

### 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

## Other comparisons with Browserbase or Puppeteer (archived MCP reference server)

- [Browserbase vs Chrome DevTools MCP](https://www.anchorterminal.com/compare/browserbase-vs-chrome-devtools-mcp.md)
- [Browserbase vs Playwright MCP](https://www.anchorterminal.com/compare/browserbase-vs-playwright-mcp.md)
- [Chrome DevTools MCP vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-puppeteer-reference-server-archived.md)
- [Playwright MCP vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/playwright-mcp-vs-puppeteer-reference-server-archived.md)

## 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.