Does it work with all three browsers out of the box?

Yes — `npx playwright install` runs the first time the MCP launches and downloads bundled builds of Chromium, Firefox, and WebKit. Pin a single engine with `BROWSER=firefox` if you want to save disk.

How does it compare to Puppeteer for an agent?

Playwright auto-waits for elements to be actionable before clicking, which removes the most common source of agent flake. Puppeteer is fine for Chromium-only flows, but Playwright is the safer default if you are starting fresh.

Can it record and replay browser sessions?

Yes. Playwright traces capture every action, network request, and DOM snapshot. The MCP exposes a trace mode that the agent can hand back to you as a single archive for post-hoc inspection.

Playwright

Name: Top MCPs — curated MCP directory
Creator: Top MCPs
License: https://creativecommons.org/licenses/by/4.0/

Official

Official Microsoft browser automation across Chromium, Firefox, and WebKit.

Score 94(?)MicrosoftApache-2.0 33kVerified May 26, 2026Top MCPs for Browser Automation →

Install View on GitHub

Quick answer

What it does

Exposes Playwright's automation surface as MCP tools: navigate, click, type, screenshot, evaluate JavaScript, and assert on page state across three real browser engines.

Best for

Cross-browser testing
Auto-wait selector reliability
Real Firefox or WebKit
Trace-based debugging

Not for

Static-HTML scraping
Bare-metal speed at scale

Setup recipe

Pick your client, then follow the three steps.

Install

claude_desktop_config.jsonjson

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": [
        "-y",
        "@playwright/mcp@latest"
      ]
    }
  }
}

Paste under mcpServers. Fully quit and reopen Claude after editing.

CLI or .mcp.jsonshell

claude mcp add playwright -- npx -y @playwright/mcp@latest

Run from your repo. Commit .mcp.json to share with your team.

.cursor/mcp.jsonjson

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": [
        "-y",
        "@playwright/mcp@latest"
      ]
    }
  }
}

Global path: ~/.cursor/mcp.json. Reload window after editing.

.vscode/mcp.jsonjsonc

{
  "servers": {
    "playwright": {
      "command": "npx",
      "args": [
        "-y",
        "@playwright/mcp@latest"
      ]
    }
  }
}

VS Code uses the "servers" key (not "mcpServers").

~/.codeium/windsurf/mcp_config.jsonjson

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": [
        "-y",
        "@playwright/mcp@latest"
      ]
    }
  }
}

Open via Cascade → hammer icon → Configure.

cline_mcp_settings.jsonjson

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": [
        "-y",
        "@playwright/mcp@latest"
      ]
    }
  }
}

Open via the Cline sidebar → MCP Servers → Edit.

~/.continue/config.jsonjson

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "stdio",
          "command": "npx",
          "args": [
            "-y",
            "@playwright/mcp@latest"
          ]
        }
      }
    ]
  }
}

Continue uses modelContextProtocolServers with a transport block.

~/.codex/config.tomlshell

# ~/.codex/config.toml
[mcp_servers.playwright]
command = "npx"
args = [
  "-y",
  "@playwright/mcp@latest",
]

Codex uses TOML. Each server is a [mcp_servers.<name>] subtable.

~/.config/zed/settings.jsonjsonc

{
  "context_servers": {
    "playwright": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "@playwright/mcp@latest"
        ]
      }
    }
  }
}

Zed calls them "context_servers". Settings live-reload on save.

ChatGPT → Apps directorynone

Playwright doesn't ship a hosted HTTPS endpoint today. ChatGPT supports remote MCP servers only — to use this server in ChatGPT you'll need to deploy it to a public HTTPS URL first (e.g. via Cloudflare Workers or Vercel) or wait for an official remote build.

2
Set required secrets
No credentials required — this MCP runs over stdio without authentication.
3
Try a minimum working prompt
Minimum working prompt pending verification. Try any prompt from the MCP’s README once installed.

Tools & permissions

Tool	Description	Args	Side effects
`browser_navigate`	Navigate to a URL.	url: string	Network
`browser_click`	Click an element.	selector: string	Exec
`browser_type`	Type text into an input.	selector: string, text: string	Exec
`browser_screenshot`	Take a screenshot.	name: string, fullPage?: boolean	Read
`browser_evaluate`	Run JavaScript in the page context.	script: string	Exec

Security & scope

Access scope: Exec
Sandbox: Spawns a real browser process under the user account. Has full network access; can execute arbitrary JS on pages it visits.
Gotchas: Three browser engines downloaded on first run (~400 MB total) unless pinned.
Downloads and uploads default to the user home directory.
Auto-wait can mask broken pages — combine with explicit assertions.

Agent prompt pack

— copy into Claude, Cursor, or ChatGPT.

Paste into Claude, Cursor, or ChatGPT. Edit the [brackets] before sending.

Recommend the best MCP servers for [task: e.g. browser automation work] in [client: Claude].

Constraints:
- Prefer tools that are [official | open-source | read-only] — pick what matters for my use case.
- Exclude MCPs that require [e.g. a paid plan, OAuth-only flows, remote-only transport].
- Return at most 3 picks, ranked.

For each pick include:
1. One-sentence rationale.
2. The ready-to-paste install snippet for my client.
3. Any required secrets I need to create before installing.

Cross-check the top-mcps.com listing: https://top-mcps.com/top-mcps-for-browser-automation

Compare Playwright against a real alternative. Swap the second MCP in [brackets] if you want a different match.

Compare Playwright MCP vs [Puppeteer MCP] for the following job: [describe the job, e.g. "let an agent create GitHub issues on bug triage"].

Judge them on:
- Setup time and complexity (what a new user hits first).
- Auth model (none / API key / OAuth 2.1) and credential risk.
- Transport (stdio / Streamable HTTP / SSE) and where the server runs.
- Required secrets and the blast radius if they leak.
- Operational risk in an unattended agent loop.
- Which one is "good enough" for a weekend prototype vs. production.

End with one sentence: which should I pick for my scenario, which is: [my scenario].

References:
- https://top-mcps.com/mcp/playwright
- top-mcps.com listing for Puppeteer

Asks the agent to install and verify. Works inside Claude Code, Cursor Agent, Codex CLI.

Install the Playwright MCP server for my [client: Claude] at the default config path for that client.

Use the exact install snippet published at https://top-mcps.com/mcp/playwright (fetch https://top-mcps.com/mcp/playwright.json for the canonical server.json if you can read URLs).

Before finishing:
1. Create the required secrets (no secrets) and put them in the appropriate env block — do not hard-code them.
2. Restart or reload the client so it picks up the new server.
3. Verify the server is connected (green / running state) and at least one tool is listed.
4. If anything fails, read the client's MCP logs and report the exact error — do not silently retry.

Confirm when done and list the tools the server now exposes.

Frequently asked questions

What changed

— 2 updates tracked.

May 26, 2026
Refreshed install snippets and fact sheet; verified for 2026.
Feb 15, 2025
Initial directory listing.

More Browser Automation MCPs

Other tools in the same category worth evaluating.

Puppeteer

Full browser automation: navigate, click, screenshot, and scrape.

browserautomationscrapingpuppeteer

5 minMedium

Browserbase

Official

Hosted, isolated Chromium runtime for AI agents that need a fresh browser per task.

browsercloudbrowserbaseautomation

5 minMedium

Stagehand

Official

AI-native browser automation: act, observe, and extract in plain English.

browserstagehandbrowserbaseai-automation

5 minMedium

Compared with Playwright

Side-by-side breakdowns for the choices people most often weigh against this MCP.

PlaywrightvsPuppeteer PlaywrightvsBrowserbase PlaywrightvsStagehand PlaywrightvsSkyvern

Exploring Top MCPs for Browser Automation? See all Browser Automation MCPs →

Quick answer

What it does

Best for

Not for

Setup recipe

Install

Set required secrets

Try a minimum working prompt

Tools & permissions

Security & scope

Agent prompt pack

Full details

Frequently asked questions

Does it work with all three browsers out of the box?

How does it compare to Puppeteer for an agent?

Can it record and replay browser sessions?

What changed

More Browser Automation MCPs

Puppeteer

Browserbase

Stagehand

Compared with Playwright