The MCP Server with Pyppeteer provides a powerful way to control headless browsers using the Multi-Context Protocol (MCP) framework. This tool enables automated web navigation, screenshot capture, and element interaction through a standardized interface that can be integrated with AI assistants.
For Claude Desktop users, the easiest installation method is via Smithery:
npx -y @smithery/cli install @devalexandre/mcp-servers --client claude
Install directly from GitHub using pip:
pip install -e git+https://github.com/devalexandre/mcp-servers.git#egg=mcp-servers
If you prefer to install from source:
git clone https://github.com/devalexandre/mcp-servers.git
cd mcp-servers
Optionally create a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows, use `venv\Scripts\activate`
pip install -r requirements.txt
Install in development mode:
pip install -e .
from mcp_servers import PyppeteerServer
# Initialize the server
server = PyppeteerServer()
await server.initialize()
# Navigate to a webpage
await server.navigate("https://example.com")
# Take a screenshot
screenshot = await server.take_screenshot()
# Close the browser when finished
await server.shutdown()
# Navigate to a page
await server.navigate("https://example.com/login")
# Click on elements using different selector methods
await server.click_element(".login-button") # CSS selector
await server.click_element("//button[@id='submit']", selector_type="xpath") # XPath
await server.click_element("btn-primary", selector_type="class") # Class name
# Get the current URL after navigation
current_url = await server.get_current_url()
For more complex automation tasks, you can chain multiple operations:
# Initialize the browser
await server.initialize()
# Navigate to a search engine
await server.navigate("https://www.google.com")
# Interact with the search input using XPath
search_xpath = "//input[@name='q']"
await server.page.type(search_xpath, "pyppeteer automation")
# Take a screenshot of the search results
screenshot = await server.take_screenshot()
# Perform cleanup
await server.shutdown()
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "pyppeteer-browser-automation" '{"command":"python","args":["-m","mcp_servers"]}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"pyppeteer-browser-automation": {
"command": "python",
"args": [
"-m",
"mcp_servers"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"pyppeteer-browser-automation": {
"command": "python",
"args": [
"-m",
"mcp_servers"
]
}
}
}
3. Restart Claude Desktop for the changes to take effect