Configurable Puppeteer MCP Server
A configurable MCP server for browser automation using Puppeteer.
Configurable Puppeteer MCP Server
A Model Context Protocol server that provides browser automation capabilities using Puppeteer with configurable options. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment, with the ability to customize Puppeteer launch options through environment variables.
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 screenshotselector(string, optional): CSS selector for element to screenshotwidth(number, optional, default: 800): Screenshot widthheight(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 fieldvalue(string): Value to fill
-
puppeteer_select
- Select an element with SELECT tag
- Inputs:
selector(string): CSS selector for element to selectvalue(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:
-
Console Logs (
console://logs)- Browser console output in text format
- Includes all console messages from the browser
-
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)
- Configurable Puppeteer options through environment variables
Configuration
Using with Custom Puppeteer Options
You can configure Puppeteer launch options by providing a JSON string in the PUPPETEER_ARGS environment variable. This allows you to customize browser behavior without modifying the server code.
Example: Using Firefox Instead of Chrome
{
"mcpServers": {
"puppeteer": {
"command": "npx",
"args": ["-y", "github:afshawnlotfi/mcp-configurable-puppeteer"],
"env": {
"PUPPETEER_ARGS": "{\"browser\": \"firefox\"}"
}
}
}
}
Example: Configuring Browser Window Size
{
"mcpServers": {
"puppeteer": {
"command": "npx",
"args": ["-y", "github:afshawnlotfi/mcp-configurable-puppeteer"],
"env": {
"PUPPETEER_ARGS": "{\"defaultViewport\": {\"width\": 1280, \"height\": 800}}"
}
}
}
}
Standard Configuration
NPX
{
"mcpServers": {
"puppeteer": {
"command": "npx",
"args": ["-y", "github:afshawnlotfi/mcp-configurable-puppeteer"]
}
}
}
You can also specify a branch, tag, or commit:
{
"mcpServers": {
"puppeteer": {
"command": "npx",
"args": ["-y", "github:afshawnlotfi/mcp-configurable-puppeteer#main"]
}
}
}
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.
संबंधित सर्वर
Bright Data
प्रायोजकDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
MCP Server Collector
Discovers and collects MCP servers from the internet.
Lightpanda Go MCP server
A Go-based MCP server for interacting with the Lightpanda Browser using the Chrome DevTools Protocol (CDP).
YouTube Translate MCP
Access YouTube video transcripts and translations using the YouTube Translate API.
Postman V2
An MCP server that provides access to Postman using V2 api version.
AgentQL
Enable AI agents to get structured data from unstructured web with AgentQL.
BrowserCat MCP Server
Remote browser automation using the BrowserCat API.
Playwright Server
Automate web browsers and perform web scraping tasks using the Playwright framework.
Haunt API
AI-powered web data extraction MCP server — extract structured JSON from any website with natural language prompts.
Novada-MCP
Search, extract, crawl, map, and research the web — from any AI agent or terminal.
Google-DeepSearch-AI-Mode
https://github.com/mottysisam/deepsearch