# Playwright MCP vs Selenium

> Selenium scores 73.6 (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-selenium
- Markdown: https://www.anchorterminal.com/compare/playwright-mcp-vs-selenium.md (~2,500 tokens)
- Slim: https://www.anchorterminal.com/compare/playwright-mcp-vs-selenium.min.md (~580 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/playwright-mcp-vs-selenium.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

Selenium scores 73.6 (BB) on agent readiness against Playwright MCP's 67.6 (B), and leads in 4 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
- Selenium: grade BB, 73.6/100, rank #90 of 1076. Markdown https://www.anchorterminal.com/tools/selenium.md · JSON https://www.anchorterminal.com/api/v1/tools/selenium.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 70
- Security & auth, 57 against 43

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

### Selenium (BB)

Good for: Agents that write test or automation scripts in any of five languages, and teams with a Grid.

Ahead on:
- Reliability, 90 against 57
- Schema & documentation, 89 against 70
- Maintenance & community, 94 against 84

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

Watch for: No MCP server from the project. The docs point to community servers and say they are third-party


## Score by category

| Category | Weight | Playwright MCP | Selenium | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 57 | 90 | Selenium +33 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 70 | 89 | Selenium +19 |
| Agent ergonomics | 13% (16.2 this run) | 84 | 70 | Playwright MCP +14 |
| Security & auth | 14% (17.5 this run) | 57 | 43 | Playwright MCP +14 |
| 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 | 94 | Selenium +10 |
| Transparency & trust | 7% (8.8 this run) | 72 | 74 | Selenium +2 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **67.6 · B** | **73.6 · BB** | |

## Facts side by side

| Fact | Playwright MCP | Selenium |
| --- | --- | --- |
| Kind | MCP server | SDK + MCP |
| Vendor | Microsoft | Selenium project (Software Freedom Conservancy) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | stdio, Streamable HTTP, SSE (legacy) | HTTP |
| 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 | yes |
| MCP registry | `io.github.microsoft/playwright-mcp` | not listed |
| Last release | 2026-09-28 | 2026-10-09 |
| 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 | 35k stars, 1.8M npm/wk, 6.9M PyPI/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.

**Selenium.** Selenium is stable, Apache-2.0 software on 4.51.0 with bindings in five languages, CI passing on trunk, an llms.txt and an agent guide added in September 2026. It has no MCP server of its own, Selenium Manager sends usage statistics by default, and Grid accepts unauthenticated sessions unless a username and password are set.

## 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

### Selenium

1. Install with `pip install selenium` (Python 3.10 or later) and let Selenium Manager fetch drivers. Do not set driver paths
2. Use `WebDriverWait` with expected conditions, never fixed sleeps, and do not mix implicit and explicit waits
3. Set `SE_AVOID_STATS=true` to stop Selenium Manager sending usage statistics
4. Point coding agents at https://www.selenium.dev/llms.txt. Most Selenium 2 and 3 era examples use removed APIs
5. Set `--username` and `--password` before exposing a Grid beyond localhost. Check `http://localhost:4444/status` before creating sessions

## Questions

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

Selenium scores 73.6 (BB) on agent readiness against Playwright MCP's 67.6 (B), and leads in 4 of 7 scored categories. Playwright MCP leads on agent ergonomics and security & auth.

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

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

### Are Playwright MCP and Selenium open source?

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


## For agents

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

## Other comparisons with Playwright MCP or Selenium

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