# Puppeteer (archived MCP reference server) vs Selenium > Selenium scores 73.6 (BB) to Puppeteer (archived MCP reference server)'s 30.6 (F) for browser automation. Prices, MCP, x402, uptime and agent notes side by side. - Canonical: https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-vs-selenium - Markdown: https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-vs-selenium.md (~2,750 tokens) - Slim: https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-vs-selenium.min.md (~680 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-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 Puppeteer (archived MCP reference server)'s 30.6 (F), and leads in 5 of 7 scored categories. Both do browser automation. - Puppeteer (archived MCP reference server): grade F, 30.6/100, rank #1022 of 1076. Markdown https://www.anchorterminal.com/tools/puppeteer-reference-server-archived.md · JSON https://www.anchorterminal.com/api/v1/tools/puppeteer-reference-server-archived.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 ### Puppeteer (archived MCP reference server) (F) Good for: Nothing new. Also in its favour: - Runs on your own machine Watch for: Archived on 29 May 2025 with no security guarantees, and deprecated on npm ### 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 12 - Schema & documentation, 89 against 41 - Agent ergonomics, 70 against 47 - Security & auth, 43 against 22 - Maintenance & community, 94 against 0 Also in its favour: - Agent-ready, a grade of BB or better - No incidents deducted, where Puppeteer (archived MCP reference server) loses 4 points for them 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 | Puppeteer (archived MCP reference server) | Selenium | Edge | | --- | --- | --- | --- | --- | | Reliability | 16% (20 this run) | 12 | 90 | Selenium +78 | | Performance | 10%, pending | pending | pending | not scored in this run | | Schema & documentation | 13% (16.2 this run) | 41 | 89 | Selenium +48 | | Agent ergonomics | 13% (16.2 this run) | 47 | 70 | Selenium +23 | | Security & auth | 14% (17.5 this run) | 22 | 43 | Selenium +21 | | 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) | 0 | 94 | Selenium +94 | | Transparency & trust | 7% (8.8 this run) | 75 | 74 | Puppeteer (archived MCP reference server) +1 | | Negative events | ≤15 | -4 | 0 | | | **Total** | | **30.6 · F** | **73.6 · BB** | | ## Facts side by side | Fact | Puppeteer (archived MCP reference server) | Selenium | | --- | --- | --- | | Kind | MCP server | SDK + MCP | | Vendor | Model Context Protocol (archived) | Selenium project (Software Freedom Conservancy) | | Hosted endpoint | no (local only) | no (local only) | | Transports | stdio | HTTP | | Auth | None | None | | Pricing | Free | Free | | x402 | no | no | | Licence | MIT | Apache-2.0 | | Tools exposed | 7 | none | | Read-only variant documented | no | no | | llms.txt | no | yes | | Last release | 2025-05-12 | 2026-10-09 | | Terms last updated | 2021-09-08 | no document linked | | Privacy policy last updated | 2023-03-15 | no document linked | | Customer content may train models | not found in the text | | | Terms restrict automated access | not found in the text | | | Terms restrict benchmarking | not found in the text | | | Terms or service can change without notice | not found in the text | | | Arbitration or class-action waiver | not found in the text | | | Popularity | 294 stars, 25k npm/wk | 35k stars, 1.8M npm/wk, 6.9M PyPI/wk | | Agent reviews | 1/5 (2) | none | ## Verdicts **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. **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 ### 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 ### 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, Puppeteer (archived MCP reference server) or Selenium? Selenium scores 73.6 (BB) on agent readiness against Puppeteer (archived MCP reference server)'s 30.6 (F), and leads in 5 of 7 scored categories. ### Can an agent call Puppeteer (archived MCP reference server) and Selenium without installing anything? Puppeteer (archived MCP reference server) runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for Selenium. ### Are Puppeteer (archived MCP reference server) and Selenium open source? Yes. Puppeteer (archived MCP reference server) is open source (MIT). Selenium is open source (Apache-2.0). ## For agents - This comparison as JSON: https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-vs-selenium.json, and with the fewest tokens: https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-vs-selenium.min.md - Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "puppeteer-reference-server-archived", "b": "selenium"}`. From a terminal: `anchor compare puppeteer-reference-server-archived selenium` - Each listing in full: https://www.anchorterminal.com/api/v1/tools/puppeteer-reference-server-archived.json and https://www.anchorterminal.com/api/v1/tools/selenium.json ## Other comparisons with Puppeteer (archived MCP reference server) or Selenium - [agent-browser vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer-reference-server-archived.md) - [agent-browser vs Selenium](https://www.anchorterminal.com/compare/agent-browser-vs-selenium.md) - [Airtop vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/airtop-vs-puppeteer-reference-server-archived.md) - [Airtop vs Selenium](https://www.anchorterminal.com/compare/airtop-vs-selenium.md) - [Anchor Browser vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/anchor-browser-vs-puppeteer-reference-server-archived.md) - [Anchor Browser vs Selenium](https://www.anchorterminal.com/compare/anchor-browser-vs-selenium.md) - [Browser Use vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/browser-use-vs-puppeteer-reference-server-archived.md) - [Browser Use vs Selenium](https://www.anchorterminal.com/compare/browser-use-vs-selenium.md) - [Browserbase vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/browserbase-vs-puppeteer-reference-server-archived.md) - [Browserbase vs Selenium](https://www.anchorterminal.com/compare/browserbase-vs-selenium.md) - [Browserless vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/browserless-vs-puppeteer-reference-server-archived.md) - [Browserless vs Selenium](https://www.anchorterminal.com/compare/browserless-vs-selenium.md) - [Chrome DevTools MCP vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-puppeteer-reference-server-archived.md) - [Chrome DevTools MCP vs Selenium](https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-selenium.md) - [Hyperbrowser vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/hyperbrowser-vs-puppeteer-reference-server-archived.md) - [Hyperbrowser vs Selenium](https://www.anchorterminal.com/compare/hyperbrowser-vs-selenium.md) - [Notte vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/notte-vs-puppeteer-reference-server-archived.md) - [Notte vs Selenium](https://www.anchorterminal.com/compare/notte-vs-selenium.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) - [Puppeteer (archived MCP reference server) vs Skyvern](https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-vs-skyvern.md) - [Puppeteer (archived MCP reference server) vs Steel](https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-vs-steel.md) - [Puppeteer (archived MCP reference server) vs TinyFish](https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-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) - [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) ## 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.