playwright-pro vs io.github.browserbase/mcp-server-browserbase
playwright-pro is a plugin bundle for AI coding tools published by alirezarezvani. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). io.github.browserbase/mcp-server-browserbase is an MCP server published by browserbase. Marketplaces we read that list it: 2 (Official MCP Registry, Docker MCP Catalog). As of our marketplace pass on 2026-10-22. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |  playwright-pro |  io.github.browserbase/mcp-server-browserbase |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 2.9.0 Forks (GitHub): 3 959 Stars (GitHub): 28 474 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 2.1.1 Downloads/month (npm): 19 182 Downloads/week (npm): 2 969 Forks (GitHub): 371 Stars (GitHub): 3 399 Not marked · First seen |
| Docker MCP Catalog | Not listed | Listed Version: sha256:f90cb76e34ba Forks (GitHub): 371 Pulls (Docker Hub): 38 240 Stars (Docker Hub): 1 Stars (GitHub): 3 399 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | playwright-pro | io.github.browserbase/mcp-server-browserbase |
|---|---|---|
| Marketplaces that list it (differs) | 1 (worse) | 2 (better) |
| Stars (GitHub) (differs) | 28 474 (better) | 3 399 (worse) |
| Pulls (Docker Hub) (differs) | No figure on Docker Hub | 38 240 |
| Forks (GitHub) (differs) | 3 959 (better) | 371 (worse) |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | Remote server or your machine |
| Transport (differs) | Not stated | stdio, Streamable HTTP |
| Tools it declares (differs) | Not published | 6 |
| Environment variables it asks for (differs) | 5, secrets among them: 2 | 3, secrets among them: 2 |
| Hooks it runs (differs) | 2 | Not published |
| Parts of the bundle (differs) | 17 | Not a bundle |
| Licence (differs) | MIT | Apache-2.0 |
| Repository (differs) | github.com/alirezarezvani/claude-skills | github.com/browserbase/mcp-server-browserbase |
| Changes in the last 7 days | 0 | 0 |
| First seen | 2026-10-11 | 2026-10-11 |
| Endpoint at the last check (differs) | no remote endpoint we check | Answered with HTTP 404 (19 h ago) |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
playwright-pro
Playwright Pro turns your AI coding agent into a senior test automation engineer. Instead of generating tutorial-quality tests with brittle CSS selectors, Playwright Pro enforces battle-tested patterns from production test suites: role-based locators, web-first assertions, proper fixture architecture, and isolated test design. It doesn't reinvent Claude Code — it orchestrates it. /pw:generate uses the built-in Explore subagent for codebase analysis. /pw:migrate delegates to /batch for parallel file conversion. /pw:fix leverages /debug for trace inspection. Every skill builds on what Claude Code already does well. 55 ready-to-use test templates across 11 categories — authentication, CRUD, checkout, search, forms, dashboard, settings, onboarding, notifications, API testing, and accessibility. Each template includes TypeScript and JavaScript variants with parametrizable placeholders. Not generic stubs — real patterns like Stripe iframe handling, GraphQL mutation testing, and RBAC permission flows. 3 specialized
io.github.browserbase/mcp-server-browserbase
MCP server for AI web browser automation using Browserbase and Stagehand
How to run each
playwright-pro As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install playwright-pro@claude-communityio.github.browserbase/mcp-server-browserbase As a local MCP server: npm package
claude mcp add --env "BROWSERBASE_API_KEY=<YOUR_BROWSERBASE_API_KEY>" --env "BROWSERBASE_PROJECT_ID=<YOUR_BROWSERBASE_PROJECT_ID>" --env "GEMINI_API_KEY=<YOUR_GEMINI_API_KEY>" --transport stdio mcp-server-browserbase -- npx -y @browserbasehq/mcp-server-browserbaseRequires: BROWSERBASE_API_KEY (secret), BROWSERBASE_PROJECT_ID, GEMINI_API_KEY (secret)
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Only io.github.browserbase/mcp-server-browserbase has a remote endpoint we check. How we check endpoints
Tools each declares
The marketplaces of playwright-pro publish no list of tools, so we do not compare tools.
Settings each asks for
Only playwright-pro asks for
BROWSERSTACK_ACCESS_KEY (secret)BROWSERSTACK_USERNAMETESTRAIL_API_KEY (secret)TESTRAIL_URLTESTRAIL_USER
Only io.github.browserbase/mcp-server-browserbase asks for
BROWSERBASE_API_KEY (secret)BROWSERBASE_PROJECT_ID (secret)GEMINI_API_KEY (secret)
Settings as each marketplace publishes them. Asking for fewer is not better in itself.
What it can do: playwright-pro · What it can do: io.github.browserbase/mcp-server-browserbase · Compare two other plugins
Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.