1.38M npm/wk is the highest download count in the entire web-browsing category. Real installations, not just stars. Cross-browser support (Chromium + Firefox + WebKit) is unique among ranked tools.
Playwright MCP
activeMicrosoft's official MCP server for Playwright. Uses accessibility snapshots instead of screenshots for structured browser control. Auto-configured in GitHub Copilot's Coding Agent.
Where it wins
Microsoft/Playwright official backing
Accessibility snapshots instead of screenshots — more reliable for structured tasks
Auto-configured in GitHub Copilot Coding Agent
MCP-native — works with any MCP-compatible host
Where to be skeptical
Token-heavy: 114K tokens/session vs 27K via CLI — well-documented 4x bloat problem
Less vision-aware than Browser Use for visual tasks
Accessibility snapshots miss visual layout information
Editorial verdict
Highest raw downloads in category (1.38M npm/wk). Cross-browser (Chromium + Firefox + WebKit). CLI mode is the token-efficient choice — 4x reduction vs MCP confirmed by 13+ independent sources. Microsoft officially recommends CLI for coding agents.
Videos
Reviews, tutorials, and comparisons from the community.
AI-Powered Test Automation with Playwright MCP, GitHub Copilot & VSCode (Playwright + TypeScript)
Let AI Explore Your Site & Write Tests with Playwright MCP!
How to Generate Playwright Tests using MCP + Copilot
Related
Chrome DevTools MCP
92Google Chrome team's official MCP server for Chrome DevTools. Gives coding agents deep debugging, performance profiling, and Core Web Vitals analysis through 26 tools across 6 categories.
Stagehand
90AI-native browser automation SDK by Browserbase with natural language selectors and act/extract/observe primitives.
Skyvern
90Vision-LLM browser automation for enterprise workflows. Combines computer vision with LLM reasoning to handle websites never seen before. YC S23 backed with CAPTCHA solving, 2FA, and proxy networks.
Vercel Agent Browser
88Token-efficient browser automation CLI for AI agents. Rust core with sub-50ms boot. Claims 93% context reduction vs Playwright MCP through ref-based element selection on accessibility snapshots.
Public evidence
Playwright MCP burns 114K tokens/session; CLI uses 27K (4x reduction). Microsoft officially recommends CLI for coding agents. Settled consensus across 13+ independent sources — not a debate.
Microsoft now officially recommends CLI for coding agent workflows and MCP for richer introspection loops. CLI companion makes Playwright the only tool that owns both sides of the CLI-over-MCP divide.
Only ranked tool supporting Chromium, Firefox, and WebKit. 25 open issues is the fewest in the category, indicating the most polished/mature codebase. Auto-configured in GitHub Copilot Coding Agent.
Playwright MCP launch hit the HN front page. Discussion covered real-world usage with Claude Code and automatic test validation workflows, signaling strong developer interest in accessibility-tree-based browser automation.
Independent analysis showing Playwright MCP's 26-tool surface causes agent decision paralysis, and reducing to 8 core tools dramatically improves performance. Validates Playwright MCP as the de facto browser-automation MCP standard others benchmark against.
Step-by-step demo of Copilot agent mode using Playwright MCP to reproduce bugs, inspect live pages via accessibility snapshots, identify fixes, and verify them — all autonomously. Shows institutional commitment to Playwright MCP as the browser layer.
Analysis of how Playwright MCP democratizes browser automation for AI agents. Notes @playwright/cli uses 4x fewer tokens than MCP mode.
Launch-day coverage noting Playwright MCP uses accessibility tree instead of screenshots. Early independent validation from a respected voice in developer tooling.
A typical browser automation task consumes 114K tokens with MCP vs 27K with CLI — a 4x difference. Documents the well-known token bloat problem that is Playwright MCP's primary weakness.
Raw GitHub source
GitHub README peek
Constrained peek so you can sanity-check the source material without leaving the site.
Playwright MCP
A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.
Playwright MCP vs Playwright CLI
This package provides MCP interface into Playwright. If you are using a coding agent, you might benefit from using the CLI+SKILLS instead.
-
CLI: Modern coding agents increasingly favor CLI–based workflows exposed as SKILLs over MCP because CLI invocations are more token-efficient: they avoid loading large tool schemas and verbose accessibility trees into the model context, allowing agents to act through concise, purpose-built commands. This makes CLI + SKILLs better suited for high-throughput coding agents that must balance browser automation with large codebases, tests, and reasoning within limited context windows.<br>Learn more about Playwright CLI with SKILLS.
-
MCP: MCP remains relevant for specialized agentic loops that benefit from persistent state, rich introspection, and iterative reasoning over page structure, such as exploratory automation, self-healing tests, or long-running autonomous workflows where maintaining continuous browser context outweighs token cost concerns.
Key Features
- Fast and lightweight. Uses Playwright's accessibility tree, not pixel-based input.
- LLM-friendly. No vision models needed, operates purely on structured data.
- Deterministic tool application. Avoids ambiguity common with screenshot-based approaches.
Requirements
- Node.js 18 or newer
- VS Code, Cursor, Windsurf, Claude Desktop, Goose, Junie or any other MCP client
Getting started
First, install the Playwright MCP server with your client.
Standard config works in most of the tools:
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": [
"@playwright/mcp@latest"
]
}
}
}
<details>
<summary>Amp</summary>
Add via the Amp VS Code extension settings screen or by updating your settings.json file:
"amp.mcpServers": {
"playwright": {
"command": "npx",
"args": [
"@playwright/mcp@latest"
]
}
}
Amp CLI Setup:
Add via the amp mcp addcommand below
amp mcp add playwright -- npx @playwright/mcp@latest
</details>
<details>
<summary>Antigravity</summary>
Add via the Antigravity settings or by updating your configuration file:
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": [
"@playwright/mcp@latest"
]
}
}
}
</details>
<details>
<summary>Claude Code</summary>
Use the Claude Code CLI to add the Playwright MCP server:
claude mcp add playwright npx @playwright/mcp@latest
</details>
<details>
<summary>Claude Desktop</summary>
Follow the MCP install guide, use the standard config above.
</details> <details> <summary>Cline</summary>Follow the instruction in the section Configuring MCP Servers
Example: Local Setup
Add the following to your cline_mcp_settings.json file:
{
"mcpServers": {
"playwright": {
"type": "stdio",
"command": "npx",
"timeout": 30,
"args": [
"-y",
"@playwright/mcp@latest"
],
"disabled": false
}
}
}
</details>
<details>
<summary>Codex</summary>