MCP server that bridges Claude Desktop (or any other local app supporting MCP) with Selenix for browser automation and testing. Enables creating
MCP server that bridges Claude Desktop (or any other local app supporting MCP) with Selenix for browser automation and testing. Enables creating, running
Before using any setup method below, enable the bridge inside Selenix:
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| get_screenshot | Capture a screenshot of the browser window |
| get_page_html | Get the page HTML with interactive elements annotated |
| get_search_html | Search page HTML by regex pattern |
| get_selected_command_info | Get DOM context for a command's target element |
| get_current_test | Get all commands in the current test |
| get_test_list | List all tests in the project |
| get_test_by_name | Get a test by its name |
| get_command_list | List all available Selenix commands |
| get_command_info | Get detailed docs for a specific command |
| get_project_info | Get project metadata |
| get_active_suite | Get the active test suite |
| get_step_results | Get pass/fail results from the last test run |
| get_logs | Get recent logs (all types), 20 per page, most recent first. Optional page param for pagination. |
| get_workspace_context | Get a summary of the current workspace |
| add_commands | Add commands to a test at a specific position |
| run_test | Run a test and wait for results (up to 2 minutes) |
| clear_and_replace_commands | Replace all commands in a test |
| fix_commands | Apply targeted fixes — update, remove, or insert commands |
{
"mcpServers": {
"selenix": {
"command": "node",
"args": [
"<npm-root-path>/@selenix/mcp-server/dist/bundle.js"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Use Microsoft’s Playwright MCP server to navigate pages, inspect accessibility snapshots, fill forms and capture browser screenshots.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Cloud-based web access with real browsers and JS rendering by ScrapingAnt
Chrome browser automation MCP server for AI agents — drives real Chrome with your profiles
Browser tasks, sessions, and recipes for MCP and HTTP automation.
A Model Context Protocol (MCP) server that enables AI assistants to interact with web browsers, local Electron applications, and mobile applications using WebdriverIO. Automate Chrome, Firefox…