loading…
Search for a command to run...
loading…
Enables browser automation using Selenium, including navigation, element interaction, screenshots, and cookie management, through both local STDIO and Streamabl
Enables browser automation using Selenium, including navigation, element interaction, screenshots, and cookie management, through both local STDIO and Streamable HTTP transports.
Deployment-ready Python MCP server for Selenium browser automation. It supports local STDIO usage and production-style Streamable HTTP at /mcp, plus health endpoints for container platforms.
browser_start, browser_stop, browser_reset, browser_statenavigate, go_back, go_forward, refreshset_window_size, open_new_tab, switch_window, close_windowfind_element, wait_for_element, click, type_textget_text, get_attribute, execute_script, scrollpage_source, screenshot, save_screenshotlist_cookies, add_cookie, delete_cookiesLocator strategies: id, name, css selector, xpath, link text, partial link text, tag name, class name.
POST /mcp and related Streamable HTTP MCP callsGET /healthzGET /readyzPOST /browser/startPOST /browser/stopIf PowerShell says Python was not found, install Python 3.11+ first. The quickest options are:
winget install Python.Python.3.12
Then close and reopen PowerShell. If python --version still opens the Microsoft Store prompt, disable the python.exe and python3.exe app execution aliases in:
Settings > Apps > Advanced app settings > App execution aliases
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
PowerShell:
python -m venv .venv
.\.venv\Scripts\Activate.ps1
pip install -e ".[dev]"
Run as a local STDIO MCP server:
selenium-mcp
Run as a Streamable HTTP MCP server:
selenium-mcp-http
Then connect MCP clients to:
http://localhost:8000/mcp
{
"mcpServers": {
"selenium": {
"command": "selenium-mcp",
"env": {
"SELENIUM_BROWSER": "chrome",
"SELENIUM_HEADLESS": "true"
}
}
}
}
Build and run with an in-container Chromium browser:
docker build -t selenium-mcp .
docker run --rm -p 8000:8000 selenium-mcp
Run with a dedicated Selenium Grid browser container:
docker compose up --build
Copy .env.example to .env and adjust:
SELENIUM_BROWSER=chrome
SELENIUM_HEADLESS=true
SELENIUM_REMOTE_URL=
SELENIUM_IMPLICIT_WAIT_SECONDS=2
SELENIUM_PAGE_LOAD_TIMEOUT_SECONDS=30
SELENIUM_SCRIPT_TIMEOUT_SECONDS=30
SELENIUM_WINDOW_WIDTH=1440
SELENIUM_WINDOW_HEIGHT=1000
SELENIUM_ALLOW_FILE_URLS=false
SELENIUM_DEFAULT_DOWNLOAD_DIR=/tmp/selenium-downloads
SELENIUM_HTTP_HOST=0.0.0.0
SELENIUM_HTTP_PORT=8000
SELENIUM_MCP_TRANSPORT=stdio
For remote Selenium Grid, set:
SELENIUM_REMOTE_URL=http://selenium:4444/wd/hub
This server can browse the web, execute JavaScript, read page HTML, and save screenshots on the host. In production, run it in a locked-down container or VM, restrict outbound network access, keep SELENIUM_ALLOW_FILE_URLS=false, and put the HTTP MCP endpoint behind your platform authentication layer.
ruff check .
pytest
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"seleniummcp": {
"command": "npx",
"args": []
}
}
}Browser automation, scraping, screenshots
Browser automation and web scraping.
Plugin-based MCP server + Chrome extension that gives AI agents access to web applications through the user's authenticated browser session. 100+ plugins with a
1,500+ developer infrastructure deals, free tiers, and startup programs across 54 categories. Search deals, compare vendors, plan stacks, and track pricing chan