Skip to main content
Glama
README.md
# Puppeteer

A Model Context Protocol server that provides browser automation capabilities using Puppeteer. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.

## Components

### Tools

- **puppeteer_navigate**
  - Navigate to any URL in the browser
  - Input: `url` (string)

- **puppeteer_screenshot**
  - Capture screenshots of the entire page or specific elements
  - Inputs:
    - `name` (string, required): Name for the screenshot
    - `selector` (string, optional): CSS selector for element to screenshot
    - `width` (number, optional, default: 800): Screenshot width
    - `height` (number, optional, default: 600): Screenshot height

- **puppeteer_click**
  - Click elements on the page
  - Input: `selector` (string): CSS selector for element to click

- **puppeteer_hover**
  - Hover elements on the page
  - Input: `selector` (string): CSS selector for element to hover

- **puppeteer_fill**
  - Fill out input fields
  - Inputs:
    - `selector` (string): CSS selector for input field
    - `value` (string): Value to fill

- **puppeteer_select**
  - Select an element with SELECT tag
  - Inputs:
    - `selector` (string): CSS selector for element to select
    - `value` (string): Value to select

- **puppeteer_evaluate**
  - Execute JavaScript in the browser console
  - Input: `script` (string): JavaScript code to execute

### Resources

The server provides access to two types of resources:

1. **Console Logs** (`console://logs`)
   - Browser console output in text format
   - Includes all console messages from the browser

2. **Screenshots** (`screenshot://<name>`)
   - PNG images of captured screenshots
   - Accessible via the screenshot name specified during capture

## Key Features

- Browser automation
- Console log monitoring
- Screenshot capabilities
- JavaScript execution
- Basic web interaction (navigation, clicking, form filling)

## Configuration to use Puppeteer Server
Here's the Claude Desktop configuration to use the Puppeter server:

### Docker

**NOTE** The docker implementation will use headless chromium, where as the NPX version will open a browser window.

```json
{
  "mcpServers": {
    "puppeteer": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "--init", "-e", "DOCKER_CONTAINER=true", "mcp/puppeteer"]
    }
  }
}
```

### NPX

```json
{
  "mcpServers": {
    "puppeteer": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-puppeteer"]
    }
  }
}
```

## Build

Docker build:

```bash
docker build -t mcp/puppeteer -f src/puppeteer/Dockerfile .
```

## License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.

TDQS

C2.9/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: make_http_request performs general HTTP requests, puppeteer_navigate navigates to URLs in a browser context, puppeteer_page_history retrieves navigation history, and semantic_search_requests searches within page requests. There is no overlap or ambiguity between these functions.

Naming Consistency3/5

The naming is mixed with no consistent pattern: make_http_request uses verb_noun format, puppeteer_navigate and puppeteer_page_history use a prefix_noun format, and semantic_search_requests uses an adjective_noun_noun format. While readable, the conventions vary without a predictable structure.

Tool Count3/5

With only 4 tools, the count feels thin for a Puppeteer server, which typically handles browser automation tasks like clicking, typing, or screenshotting. The tools cover basic navigation and HTTP requests but lack broader automation capabilities, making the scope borderline under-scoped.

Completeness2/5

For a Puppeteer server, there are significant gaps in the tool surface. Missing are core operations like interacting with page elements (e.g., click, type), evaluating scripts, taking screenshots, or managing browser contexts. The tools provided focus narrowly on navigation and HTTP requests, leaving major automation workflows uncovered.

Maintenance

ActivityInactive
ResponsivenessNo issues