How do I configure custom Puppeteer options?
Set the `PUPPETEER_ARGS` environment variable to a JSON string of Puppeteer launch options, such as `{"browser": "firefox"}` or `{"defaultViewport": {"width": 1280, "height": 800}}`.
@afshawnlotfi
Basic information
Configurable Puppeteer MCP Server
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"puppeteer": {
"command": "npx",
"args": [
"-y",
"github:afshawnlotfi/mcp-configurable-puppeteer"
],
"env": {
"PUPPETEER_ARGS": "{\"browser\": \"firefox\"}"
}
}
}
}Navigate to any URL in the browser
Capture screenshots of the entire page or specific elements
Click elements on the page
Hover elements on the page
Fill out input fields
Select an element with SELECT tag
Execute JavaScript in the browser console
Configurable Puppeteer MCP Server is a Model Context Protocol server that provides browser automation capabilities using Puppeteer with configurable launch options. It enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment, with customization through environment variables.
Use the NPX command npx -y github:afshawnlotfi/mcp-configurable-puppeteer in your MCP client configuration. Optionally set the PUPPETEER_ARGS environment variable to a JSON string of custom Puppeteer launch options (e.g., to use Firefox or set viewport size).
Set the `PUPPETEER_ARGS` environment variable to a JSON string of Puppeteer launch options, such as `{"browser": "firefox"}` or `{"defaultViewport": {"width": 1280, "height": 800}}`.
Tools include `puppeteer_navigate`, `puppeteer_screenshot`, `puppeteer_click`, `puppeteer_hover`, `puppeteer_fill`, `puppeteer_select`, and `puppeteer_evaluate`.
Screenshots are accessible via the resource `screenshot://<name>`, where `<name>` is the name provided during capture.
The server provides console logs at `console://logs` (text format) and screenshots at `screenshot://<name>` (PNG images).
Use the `puppeteer_evaluate` tool with the `script` input containing the JavaScript code to execute.
Loadster is a load testing, stress testing, and synthetic monitoring platform. Run Playwright, Browser Bots, and Protocol Bots to test and monitor your websites, web apps, and APIs. Loadster MCP gives your agents the abi
Browse the web, directly from Cursor etc.
DOM-first AI browser automation for Chrome and MCP clients.
MCP server paired with a browser extension that enables AI agents to control the user's browser.
A flexible HTTP fetching Model Context Protocol server.
Comments