Playwright

Name: Playwright
Author: executeautomation

CAUTIONgrade C · trust 77/100

Playwright Model Context Protocol Server - Tool to automate Browsers and APIs in Claude Desktop, Cline, Cursor IDE and More 🔌

Overview

From the repository's own README, as read at the audited commit.

<div align="center" markdown="1">  <table>    <tr>      <td align="center" valign="middle">        <a href="https://mseep.ai/app/executeautomation-mcp-playwright">          <img src="https://mseep.net/pr/executeautomation-mcp-playwright-badge.png" alt="MseeP.ai Security Assessment Badge" height="80"/>        </a>      </td>    </tr>    <tr>      <td align="center"><sub>MseeP.ai Security Assessment</sub></td>    </tr>  </table></div><hr># Playwright MCP Server 🎭[![Trust Score](https://archestra.ai/mcp-catalog/api/badge/quality/executeautomation/mcp-playwright)](https://archestra.ai/mcp-catalog/executeautomation__mcp-playwright)[![smithery badge](https://smithery.ai/badge/@executeautomation/playwright-mcp-server)](https://smithery.ai/server/@executeautomation/playwright-mcp-server)A Model Context Protocol server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages, take screenshots, generate test code, web scrapes the page and execute JavaScript in a real browser environment.<a href="https://glama.ai/mcp/servers/yh4lgtwgbe"><img width="380" height="200" src="https://glama.ai/mcp/servers/yh4lgtwgbe/badge" alt="mcp-playwright MCP server" /></a>## ✨ What's New in v1.0.10### 🎯 Device Emulation with 143 Real Device Presets!Test your web applications on **real device profiles** with a simple command:```javascript// Test on iPhone 13 with automatic user-agent, touch support, and device pixel ratioawait playwright_resize({ device: "iPhone 13" });// Switch to iPad with landscape orientationawait playwright_resize({ device: "iPad Pro 11", orientation: "landscape" });// Test desktop viewawait playwright_resize({ device: "Desktop Chrome" });```**Natural Language Support for AI Assistants:**- "Test on iPhone 13" - "Switch to iPad view"- "Rotate to landscape"**Supports 143 devices:** iPhone, iPad, Pixel, Galaxy, and Desktop browsers with proper emulation of viewport, user-agent, touch events, and device pixel ratios.📚 [

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code

claude mcp add playwright-mcp-server -- npx -y @executeautomation/[email protected]

claude-desktop

{
  "mcpServers": {
    "playwright-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@executeautomation/[email protected]"
      ]
    }
  }
}

Exposed tools (33) 22 read · 9 write · 2 destructive

Blast radius: 2 tools can delete or overwrite. An agent that can be talked into calling a tool can be talked into calling this one.

Tool	Risk	Description
`clear_codegen_session`	destructive	Clear a code generation session without generating a test
`end_codegen_session`	read	End a code generation session and generate the test file
`get_codegen_session`	read	Get information about a code generation session
`playwright_assert_response`	read	Wait for and validate a previously initiated HTTP response wait operation.
`playwright_click`	read	Click an element on the page
`playwright_click_and_switch_tab`	read	Click a link and switch to the newly opened tab
`playwright_close`	read	Close the browser and release all resources
`playwright_console_logs`	read	Retrieve console logs from the browser with filtering options
`playwright_custom_user_agent`	write	Set a custom User Agent for the browser
`playwright_delete`	destructive	Perform an HTTP DELETE request
`playwright_drag`	read	Drag an element to a target location
`playwright_evaluate`	write	Execute JavaScript in the browser console
`playwright_expect_response`	write	Ask Playwright to start waiting for a HTTP response. This tool initiates the wait operation but does not wait for its completion.
`playwright_fill`	read	fill out an input field
`playwright_get`	read	Perform an HTTP GET request
`playwright_get_visible_html`	read	Get the HTML content of the current page. By default, all <script> tags are removed from the output unless removeScripts is explicitly set to false.
`playwright_get_visible_text`	read	Get the visible text content of the current page
`playwright_go_back`	read	Navigate back in browser history
`playwright_go_forward`	read	Navigate forward in browser history
`playwright_hover`	read	Hover an element on the page
`playwright_iframe_click`	read	Click an element in an iframe on the page
`playwright_iframe_fill`	read	Fill an element in an iframe on the page
`playwright_navigate`	read	Navigate to a URL
`playwright_patch`	write	Perform an HTTP PATCH request
`playwright_post`	write	Perform an HTTP POST request
`playwright_press_key`	read	Press a keyboard key
`playwright_put`	write	Perform an HTTP PUT request
`playwright_resize`	read	Resize the browser viewport using manual dimensions or device presets. Supports 143+ device presets including iPhone, iPad, Android devices, and desktop browsers with proper user-agent and touch emulation.
`playwright_save_as_pdf`	write	Save the current page as a PDF file
`playwright_screenshot`	read	Take a screenshot of the current page or a specific element
`playwright_select`	read	Select an element on the page with Select tag
`playwright_upload_file`	write	Upload a file to an input[type=
`start_codegen_session`	write	Start a new code generation session to record Playwright actions

Details

Source: executeautomation/mcp-playwright
npm: @executeautomation/playwright-mcp-server@1.0.12
Transports: sse · stdio
License: MIT
Stars: 5,644 · pushed 274d ago

Trust audit

Install with care. The audit found things worth knowing before you trust its output.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	WARN
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	WARN
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (1 observation(s))
Network: declared (1 observation(s))
Shell: declared (2 observation(s))
Dependencies: not all pinned
Secrets in source: found

Findings (21)

MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321

docs/docs/playwright-api/Examples.md:19

token: 'your-bearer-token-here'

MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321

docs/docs/playwright-api/Examples.md:26

token: 'your-bearer-token-here'

MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321

docs/docs/playwright-api/Examples.md:32

token: 'your-bearer-token-here'

MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321

docs/docs/playwright-api/Examples.md:88

token: 'this-will-be-ignored',

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59

clear_codegen_session, playwright_delete

Why it matters. 2 tool(s) can delete or overwrite

Fix. prefer a read-only mode or scoped tokens; the page states the blast radius

LOWInventory / provenance · inv.hidden_file · CWE-1104

docs/static/.nojekyll

.nojekyll

Why it matters. hidden member outside the usual dotfiles

Fix. review its purpose

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

src/__tests__/codegen.test.ts:12

OUTPUT_DIR: path.join(__dirname, '../../tests/generated'),

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

src/__tests__/tools/api/requests.test.ts:1

import { GetRequestTool, PostRequestTool, PutRequestTool, PatchRequestTool, DeleteRequestTool } from '../../../tools/api/requests.js';

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

src/__tests__/tools/api/requests.test.ts:2

import { ToolContext } from '../../../tools/common/types.js';

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

src/__tests__/tools/browser/advancedInteraction.test.ts:1

import { DragTool, PressKeyTool } from '../../../tools/browser/interaction.js';

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

src/__tests__/tools/browser/advancedInteraction.test.ts:2

import { ToolContext } from '../../../tools/common/types.js';

LOWNetwork egress · net.raw_ip · CWE-200, CWE-319

docs/docs/playwright-web/HTTP-SSE-Transport.mdx:646

proxy_pass http://127.0.0.1:8931;

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357

docs/package.json

@mdx-js/react, clsx, gh-pages, prism-react-renderer, react, react-dom, typescript

Why it matters. 7 dependency range(s) float

Fix. pin exact versions or ship a lockfile

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357

package.json

@playwright/test, cors, express, mcp-evals, @types/cors, @types/express, @types/jest, @types/node

Why it matters. 12 dependency range(s) float

Fix. pin exact versions or ship a lockfile

LOWPrompt injection · prompt.credential_read · CWE-94, CWE-1427

README.md:299

The evals package loads an mcp client that then runs the index.ts file, so there is no need to rebuild between tests. You can load environment variables by prefixing the npx command. Full documentatio

Why it matters. asks the agent to read credentials

LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427

docs/docs/playwright-api/Examples.md:115

Perform POST operation for the URL https://api.restful-api.dev/objects with Bearer token "your-token-here" set in the headers

Why it matters. an instruction to move sensitive data to an outside destination

Fix. remove; a skill never needs the user's secrets off the machine