SeleniumMCP
Enables browser automation using Selenium, including navigation, element interaction, screenshots, and cookie management, through both local STDIO and Streamable HTTP transports.
README
Selenium MCP Server
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.
Tools
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_cookies
Locator strategies: id, name, css selector, xpath, link text, partial link text, tag name, class name.
HTTP Endpoints
POST /mcpand related Streamable HTTP MCP callsGET /healthzGET /readyzPOST /browser/startPOST /browser/stop
Local Setup
Windows Python Prerequisite
If 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
Claude Desktop Example
{
"mcpServers": {
"selenium": {
"command": "selenium-mcp",
"env": {
"SELENIUM_BROWSER": "chrome",
"SELENIUM_HEADLESS": "true"
}
}
}
}
Docker
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
Configuration
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
Security Notes
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.
Validation
ruff check .
pytest
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.