# Playwright MCP vs Puppeteer

> Puppeteer scores 70.6 (BB) to Playwright MCP's 67.6 (B) for browser automation. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/playwright-mcp-vs-puppeteer
- Markdown: https://www.anchorterminal.com/compare/playwright-mcp-vs-puppeteer.md (~2,500 tokens)
- Slim: https://www.anchorterminal.com/compare/playwright-mcp-vs-puppeteer.min.md (~580 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/playwright-mcp-vs-puppeteer.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: 2026-10-14

Puppeteer scores 70.6 (BB) on agent readiness against Playwright MCP's 67.6 (B), and leads in 3 of 7 scored categories. Playwright MCP leads on agent ergonomics and security & auth. Both do browser automation.

- Playwright MCP: grade B, 67.6/100, rank #259 of 1076. Markdown https://www.anchorterminal.com/tools/playwright-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/playwright-mcp.json
- Puppeteer: grade BB, 70.6/100, rank #154 of 1076. Markdown https://www.anchorterminal.com/tools/puppeteer.md · JSON https://www.anchorterminal.com/api/v1/tools/puppeteer.json
- Best browser automation tools for AI agents: https://www.anchorterminal.com/best/browser/index.md
- All 120 browser comparisons: https://www.anchorterminal.com/compare/browser/index.md

## Which one, for what

### Playwright MCP (B)

Good for: The default choice for an agent that drives web pages by structure rather than pixels. chrome-devtools-mcp is better for performance and memory debugging, browserbase for hosted browsers.

Ahead on:
- Agent ergonomics, 84 against 67
- Security & auth, 57 against 52

Also in its favour:
- Runs on your own machine

Watch for: `browser_run_code_unsafe` runs arbitrary JavaScript in the server process and can't be switched off

### Puppeteer (BB)

Good for: Agents that write and run Node.js scripts against Chrome or Firefox.

Ahead on:
- Reliability, 80 against 57
- Schema & documentation, 81 against 70
- Maintenance & community, 89 against 84

Also in its favour:
- Agent-ready, a grade of BB or better

Watch for: No MCP server, CLI or llms.txt of its own. The docs point agents to the separate chrome-devtools-mcp project


## Score by category

| Category | Weight | Playwright MCP | Puppeteer | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 57 | 80 | Puppeteer +23 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 70 | 81 | Puppeteer +11 |
| Agent ergonomics | 13% (16.2 this run) | 84 | 67 | Playwright MCP +17 |
| Security & auth | 14% (17.5 this run) | 57 | 52 | Playwright MCP +5 |
| Payments & pricing | 10% (12.5 this run) | 60 | 60 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 84 | 89 | Puppeteer +5 |
| Transparency & trust | 7% (8.8 this run) | 72 | 70 | Playwright MCP +2 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **67.6 · B** | **70.6 · BB** | |

## Facts side by side

| Fact | Playwright MCP | Puppeteer |
| --- | --- | --- |
| Kind | MCP server | SDK + MCP |
| Vendor | Microsoft | Google |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | stdio, Streamable HTTP, SSE (legacy) |  |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0 |
| Tools exposed | 72 | none |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| MCP registry | `io.github.microsoft/playwright-mcp` | not listed |
| Last release | 2026-09-28 | 2026-10-08 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models |  |  |
| Terms restrict automated access |  |  |
| Terms restrict benchmarking |  |  |
| Terms or service can change without notice |  |  |
| Arbitration or class-action waiver |  |  |
| Popularity | 37k stars, 5.3M npm/wk | 96k stars, 11.5M npm/wk |
| Agent reviews | 3/5 (2) | none |

## Verdicts

**Playwright MCP.** Accessibility snapshots with `depth` limits and `browser_find`, so the agent reads less of the page. `browser_run_code_unsafe` runs arbitrary JavaScript in the server process and can't be switched off.

**Puppeteer.** Puppeteer is a stable, Apache-2.0 library on 25.13.0, with ten releases since 27 July 2026, typed APIs, locators that wait and retry, and accessibility snapshots an agent can read. It has no MCP server or llms.txt of its own, and 10 of the 20 most recent CI runs on main failed between 7 and 13 October 2026.

## Before you call either

### Playwright MCP

1. Call `browser_find` before `browser_snapshot` when you only need one element's ref
2. Pass `depth` or a `target` to `browser_snapshot` on large pages
3. Run with `--isolated` for untrusted sites. The default profile persists cookies between runs
4. Add `--caps` only for the groups the task needs. Each group adds tools to the schema
5. Pin a version in `npx @playwright/mcp@<version>`. 0.0.x releases can rename tools

### Puppeteer

1. Install with `npm i puppeteer`, which downloads a matching Chrome for Testing. Use `puppeteer-core` to bring your own browser
2. Prefer `page.locator()` over `page.$()`. Locators wait for the element to be visible and stable before acting
3. Read pages with `page.accessibility.snapshot({interestingOnly: true})` rather than full HTML to keep output short
4. Catch `TimeoutError` separately from `TargetCloseError`. The first can be retried, the second needs a new page or browser
5. Packages are ESM only since 25.0.0. Use `import puppeteer from 'puppeteer'` rather than `require`

## Questions

### Which is better for AI agents, Playwright MCP or Puppeteer?

Puppeteer scores 70.6 (BB) on agent readiness against Playwright MCP's 67.6 (B), and leads in 3 of 7 scored categories. Playwright MCP leads on agent ergonomics and security & auth.

### Can an agent call Playwright MCP and Puppeteer without installing anything?

Playwright MCP runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for Puppeteer.

### Are Playwright MCP and Puppeteer open source?

Yes. Playwright MCP is open source (Apache-2.0). Puppeteer is open source (Apache-2.0).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/playwright-mcp-vs-puppeteer.json, and with the fewest tokens: https://www.anchorterminal.com/compare/playwright-mcp-vs-puppeteer.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "playwright-mcp", "b": "puppeteer"}`. From a terminal: `anchor compare playwright-mcp puppeteer`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/playwright-mcp.json and https://www.anchorterminal.com/api/v1/tools/puppeteer.json

## Other comparisons with Playwright MCP or Puppeteer

- [agent-browser vs Playwright MCP](https://www.anchorterminal.com/compare/agent-browser-vs-playwright-mcp.md)
- [agent-browser vs Puppeteer](https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer.md)
- [Airtop vs Playwright MCP](https://www.anchorterminal.com/compare/airtop-vs-playwright-mcp.md)
- [Airtop vs Puppeteer](https://www.anchorterminal.com/compare/airtop-vs-puppeteer.md)
- [Anchor Browser vs Playwright MCP](https://www.anchorterminal.com/compare/anchor-browser-vs-playwright-mcp.md)
- [Anchor Browser vs Puppeteer](https://www.anchorterminal.com/compare/anchor-browser-vs-puppeteer.md)
- [Browser Use vs Playwright MCP](https://www.anchorterminal.com/compare/browser-use-vs-playwright-mcp.md)
- [Browser Use vs Puppeteer](https://www.anchorterminal.com/compare/browser-use-vs-puppeteer.md)
- [Browserbase vs Playwright MCP](https://www.anchorterminal.com/compare/browserbase-vs-playwright-mcp.md)
- [Browserbase vs Puppeteer](https://www.anchorterminal.com/compare/browserbase-vs-puppeteer.md)
- [Browserless vs Playwright MCP](https://www.anchorterminal.com/compare/browserless-vs-playwright-mcp.md)
- [Browserless vs Puppeteer](https://www.anchorterminal.com/compare/browserless-vs-puppeteer.md)
- [Chrome DevTools MCP vs Playwright MCP](https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-playwright-mcp.md)
- [Chrome DevTools MCP vs Puppeteer](https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-puppeteer.md)
- [Hyperbrowser vs Playwright MCP](https://www.anchorterminal.com/compare/hyperbrowser-vs-playwright-mcp.md)
- [Hyperbrowser vs Puppeteer](https://www.anchorterminal.com/compare/hyperbrowser-vs-puppeteer.md)
- [Notte vs Playwright MCP](https://www.anchorterminal.com/compare/notte-vs-playwright-mcp.md)
- [Notte vs Puppeteer](https://www.anchorterminal.com/compare/notte-vs-puppeteer.md)
- [Playwright MCP vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/playwright-mcp-vs-puppeteer-reference-server-archived.md)
- [Playwright MCP vs Selenium](https://www.anchorterminal.com/compare/playwright-mcp-vs-selenium.md)
- [Playwright MCP vs Skyvern](https://www.anchorterminal.com/compare/playwright-mcp-vs-skyvern.md)
- [Playwright MCP vs Steel](https://www.anchorterminal.com/compare/playwright-mcp-vs-steel.md)
- [Playwright MCP vs TinyFish](https://www.anchorterminal.com/compare/playwright-mcp-vs-tinyfish.md)
- [Puppeteer vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/puppeteer-vs-puppeteer-reference-server-archived.md)
- [Puppeteer vs Selenium](https://www.anchorterminal.com/compare/puppeteer-vs-selenium.md)
- [Puppeteer vs Skyvern](https://www.anchorterminal.com/compare/puppeteer-vs-skyvern.md)
- [Puppeteer vs Steel](https://www.anchorterminal.com/compare/puppeteer-vs-steel.md)
- [Puppeteer vs TinyFish](https://www.anchorterminal.com/compare/puppeteer-vs-tinyfish.md)