# io.github.dinesh-nalla-se/playwright-mcp (npm · @dinesh-nalla-se/playwright-mcp)

Playwright Tools for MCP

- Trust score: 64/100 (medium)
- Change this week: −14
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@dinesh-nalla-se/playwright-mcp`: 64/100 (this document), [markdown](https://verifymcp.io/servers/dinesh-nalla-se-playwright-mcp/dinesh-nalla-se-playwright-mcp.md), [page](https://verifymcp.io/servers/dinesh-nalla-se-playwright-mcp/dinesh-nalla-se-playwright-mcp)
- oci · `docker.io/dineshn51331/playwright-mcp:1.0.0`: 6/100, [markdown](https://verifymcp.io/servers/dinesh-nalla-se-playwright-mcp/docker-io-dineshn51331-playwright-mcp-1-0-0.md), [page](https://verifymcp.io/servers/dinesh-nalla-se-playwright-mcp/docker-io-dineshn51331-playwright-mcp-1-0-0)

## Channel facts

- Registry: `npm`
- Package: `@dinesh-nalla-se/playwright-mcp`
- Version: `0.0.47`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 1 of 3 dependencies flagged as unhealthy (1 deprecated).
- **Provenance & Transparency**: 44/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 258 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1243 tokens (~56/item across 22 items; 22 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add dinesh-nalla-se-playwright-mcp -- npx -y @dinesh-nalla-se/playwright-mcp
```

### Codex

```bash
codex mcp add dinesh-nalla-se-playwright-mcp -- npx -y @dinesh-nalla-se/playwright-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dinesh-nalla-se-playwright-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@dinesh-nalla-se/playwright-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dinesh-nalla-se-playwright-mcp --command npx --arg -y --arg @dinesh-nalla-se/playwright-mcp
```

### Hermes

```yaml
mcp_servers:
  dinesh-nalla-se-playwright-mcp:
    command: "npx"
    args: ["-y", "@dinesh-nalla-se/playwright-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "dinesh-nalla-se-playwright-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@dinesh-nalla-se/playwright-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 64, +14)

- [security improvement] Malware scan: unverified → pass
- [functional regression] Dependency health: 0.90 → 0.80

### 2026-08-01 (score 50, −10)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 60, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 78, +32)

- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: pass

### 2026-07-26 (score 46)

First indexed and scored.

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

## MCP tools (22)

### `browser_close` (~12 tokens)

Close the page

### `browser_resize` (~37 tokens)

Resize the browser window

Input parameters:

- `height` (number, required): Height of the browser window
- `width` (number, required): Width of the browser window

### `browser_console_messages` (~26 tokens)

Returns all console messages

Input parameters:

- `onlyErrors` (boolean): Only return error messages

### `browser_handle_dialog` (~44 tokens)

Handle a dialog

Input parameters:

- `accept` (boolean, required): Whether to accept the dialog.
- `promptText` (string): The text of the prompt in case of a prompt dialog.

### `browser_evaluate` (~81 tokens)

Evaluate JavaScript expression on page or element

Input parameters:

- `element` (string): Human-readable element description used to obtain permission to interact with the element
- `function` (string, required): () => { /* code */ } or (element) => { /* code */ } when element is provided
- `ref` (string): Exact target element reference from the page snapshot

### `browser_file_upload` (~46 tokens)

Upload one or multiple files

Input parameters:

- `paths` (array): The absolute paths to the files to upload. Can be single file or multiple files. If omitted, file chooser is cancelled.

### `browser_fill_form` (~25 tokens)

Fill multiple form fields

Input parameters:

- `fields` (array, required): Fields to fill in

### `browser_install` (~30 tokens)

Install the browser specified in the config. Call this if you get an error about the browser not being installed.

### `browser_press_key` (~44 tokens)

Press a key on the keyboard

Input parameters:

- `key` (string, required): Name of the key to press or a character to generate, such as `ArrowLeft` or `a`

### `browser_type` (~112 tokens)

Type text into editable element

Input parameters:

- `element` (string, required): Human-readable element description used to obtain permission to interact with the element
- `ref` (string, required): Exact target element reference from the page snapshot
- `slowly` (boolean): Whether to type one character at a time. Useful for triggering key handlers in the page. By default entire text is filled in at once.
- `submit` (boolean): Whether to submit entered text (press Enter after)
- `text` (string, required): Text to type into the element

### `browser_navigate` (~26 tokens)

Navigate to a URL

Input parameters:

- `url` (string, required): The URL to navigate to

### `browser_navigate_back` (~17 tokens)

Go back to the previous page

### `browser_network_requests` (~18 tokens)

Returns all network requests since loading the page

### `browser_run_code` (~70 tokens)

Run Playwright code snippet

Input parameters:

- `code` (string, required): Playwright code snippet to run. The snippet should access the `page` object to interact with the page. Can make multiple statements. For example: `await page.getByRole('button', { name: 'Submit' }).c…

### `browser_take_screenshot` (~203 tokens)

Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.

Input parameters:

- `element` (string): Human-readable element description used to obtain permission to screenshot the element. If not provided, the screenshot will be taken of viewport. If element is provided, ref must be provided too.
- `filename` (string): File name to save the screenshot to. Defaults to `page-{timestamp}.{png|jpeg}` if not specified. Prefer relative file names to stay within the output directory.
- `fullPage` (boolean): When true, takes a screenshot of the full scrollable page, instead of the currently visible viewport. Cannot be used with element screenshots.
- `ref` (string): Exact target element reference from the page snapshot. If not provided, the screenshot will be taken of viewport. If ref is provided, element must be provided too.
- `type` (string): Image format for the screenshot. Default is png.

### `browser_snapshot` (~22 tokens)

Capture accessibility snapshot of the current page, this is better than screenshot

### `browser_click` (~94 tokens)

Perform click on a web page

Input parameters:

- `button` (string): Button to click, defaults to left
- `doubleClick` (boolean): Whether to perform a double click instead of a single click
- `element` (string, required): Human-readable element description used to obtain permission to interact with the element
- `modifiers` (array): Modifier keys to press
- `ref` (string, required): Exact target element reference from the page snapshot

### `browser_drag` (~94 tokens)

Perform drag and drop between two elements

Input parameters:

- `endElement` (string, required): Human-readable target element description used to obtain the permission to interact with the element
- `endRef` (string, required): Exact target element reference from the page snapshot
- `startElement` (string, required): Human-readable source element description used to obtain the permission to interact with the element
- `startRef` (string, required): Exact source element reference from the page snapshot

### `browser_hover` (~49 tokens)

Hover over element on page

Input parameters:

- `element` (string, required): Human-readable element description used to obtain permission to interact with the element
- `ref` (string, required): Exact target element reference from the page snapshot

### `browser_select_option` (~76 tokens)

Select an option in a dropdown

Input parameters:

- `element` (string, required): Human-readable element description used to obtain permission to interact with the element
- `ref` (string, required): Exact target element reference from the page snapshot
- `values` (array, required): Array of values to select in the dropdown. This can be a single value or multiple values.

### `browser_tabs` (~54 tokens)

List, create, close, or select a browser tab.

Input parameters:

- `action` (string, required): Operation to perform
- `index` (number): Tab index, used for close/select. If omitted for close, current tab is closed.

### `browser_wait_for` (~63 tokens)

Wait for text to appear or disappear or a specified time to pass

Input parameters:

- `text` (string): The text to wait for
- `textGone` (string): The text to wait for to disappear
- `time` (number): The time to wait in seconds

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/dinesh-nalla-se-playwright-mcp/dinesh-nalla-se-playwright-mcp#diagnostics

## Score history

- 2026-08-03: 64
- 2026-08-02: 64
- 2026-08-01: 50
- 2026-07-31: 60
- 2026-07-29: 78
- 2026-07-28: 78
- 2026-07-27: 78
- 2026-07-26: 46

## Links

- npm package: https://www.npmjs.com/package/@dinesh-nalla-se/playwright-mcp
- Socket report: https://socket.dev/npm/package/@dinesh-nalla-se/playwright-mcp
- Repository: https://github.com/dinesh-nalla-se/playwright-mcp
- Changelog RSS feed: https://verifymcp.io/servers/dinesh-nalla-se-playwright-mcp/dinesh-nalla-se-playwright-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/dinesh-nalla-se-playwright-mcp/dinesh-nalla-se-playwright-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/dinesh-nalla-se-playwright-mcp/dinesh-nalla-se-playwright-mcp