Playwright CdpBLOCK
Model Context Protocol server for Playwright with Chrome DevTools Protocol support
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/lars-hagen/mcp-playwright-cdp/actions/workflows/node.js.yml) [](https://github.com/lars-hagen/mcp-playwright-cdp/blob/main/LICENSE) [](https://github.com/lars-hagen/mcp-playwright-cdp/blob/main/SECURITY.md)
A Model Context Protocol server that provides browser automation capabilities using Playwright with Chrome DevTools Protocol (CDP) support. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment, with the ability to connect to existing Chrome instances via CDP.
Maintenance status
This project is in maintenance mode. Focused fixes for security, compatibility, and documentation are welcome. It is not currently published to the npm registry. The latest source release is the v0.2.10 Git tag from February 2025.
This is a fork of executeautomation/mcp-playwright v0.2.7, enhanced with CDP support for connecting to running Chrome instances.
Key Features
- 🔗 Connect to existing Chrome instances via CDP
- 🌐 Full browser automation capabilities
- 📸 Screenshot capture of entire pages or specific elements
- 🖱️ Comprehensive web interactions (navigation, clicking, form filling)
- 📊 Console log monitoring
- 🔧 JavaScript execution in browser context
- 🌍 HTTP API testing support
Installation
You can install the package using either npm or Smithery:
Installing via Smithery
To install MCP Playwright CDP for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @lars-hagen/mcp-playwright-cdp --client claude
Manual Installation
Clone the repository, then build it with
79968090945eOBSERVED · 2026-10-08Connect
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 mcp add mcp-playwright-cdp -- npx -y @lars-hagen/[email protected]
{
"mcpServers": {
"mcp-playwright-cdp": {
"command": "npx",
"args": [
"-y",
"@lars-hagen/[email protected]"
]
}
}
}Exposed tools (12)
7 read · 4 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
playwright_click | read | Click an element on the page |
playwright_delete | destructive | Perform an HTTP DELETE request |
playwright_evaluate | write | Execute JavaScript in the browser console |
playwright_fill | read | fill out an input field |
playwright_get | read | Perform an HTTP GET request |
playwright_hover | read | Hover an element 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_put | write | Perform an HTTP PUT request |
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 |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| 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
- none-observed
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (18)
const result = eval(script);
playwright_delete
.DS_Store
.DS_Store
.DS_Store
.DS_Store
.DS_Store
.DS_Store
.DS_Store
.DS_Store
.DS_Store
.nojekyll
@docusaurus/core, @docusaurus/preset-classic, @mdx-js/react, clsx, gh-pages, prism-react-renderer, react, react-dom
@types/node, typescript
docs/docs/playwright-api/img/api-response.png
docs/docs/playwright-api/img/playwright-api.png
docs/docs/playwright-web/img/mcp-result.png
image/playwright_claude.png
Gates applied: no_behavioural_pass.
79968090945efull audit observations/trust-audit/mcp-server/lars-hagen__playwright-cdp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 79968090945e | BLOCK | D | 69 | first audit |
Questions
What is the Playwright Cdp MCP server?
Model Context Protocol server for Playwright with Chrome DevTools Protocol support
What tools does Playwright Cdp expose?
12 in total: 7 read-only, 4 that write, and 1 that can delete or overwrite (playwright_delete). Every one is listed on this page with its risk.
Is Playwright Cdp safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Playwright Cdp need?
No credential environment variables were found in its source, so it appears to need none.
How does Playwright Cdp run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @lars-hagen/mcp-playwright-cdp at 0.2.10.
How current is this page?
The grade is for one exact copy of the source (79968090945e), read on 2026-10-08. The repository is watched and re-audited when it changes.