MCP
Alumnium’s Model Context Protocol server enables general-purpose AI agents like Claude Code to leverage Alumnium’s web and mobile automation capabilities through the standardized Model Context Protocol. This integration allows AI assistants to control browsers and mobile applications directly.
Installation
Section titled “Installation”The MCP Server is included in the Alumnium package for Python.
It’s recommended to use uv to automatically install Python and manage virtual environments. Follow official installation instructions to set it up on your system. Once installed, proceed to install Alumnium MCP server.
Claude Code
Section titled “Claude Code”claude mcp add alumnium --env OPENAI_API_KEY=... -- uvx --from alumnium alumnium-mcpcodex mcp add alumnium --env OPENAI_API_KEY=... -- uvx --from alumnium alumnium-mcpCursor
Section titled “Cursor”Add the the following to mcp.json:
{ "mcpServers": { "alumnium": { "command": "uvx", "args": ["--from", "alumnium", "alumnium-mcp"], "env": { "OPENAI_API_KEY": "..." } } }}Gemini CLI
Section titled “Gemini CLI”gemini mcp add alumnium --env OPENAI_API_KEY=... uvx --from alumnium alumnium-mcpVisual Studio Code
Section titled “Visual Studio Code”code --add-mcp '{ "name": "alumnium", "command": "uvx", "args": [ "--from", "alumnium", "alumnium-mcp" ], "env": { "OPENAI_API_KEY": "..." } }'The MCP Server exposes Alumnium’s core automation capabilities:
| Tool | Description |
|---|---|
start_driver | Initialize browser/mobile drivers with Appium/Selenium/Playwright capabilities |
stop_driver | Cleanup resources and retrieve token usage statistics |
do | Execute natural language automation commands |
check | Verify statements about the current page state with optional vision support |
get | Extract data from pages using natural language descriptions |
fetch_accessibility_tree | Debug page structure with raw accessibility tree |
start_driver
Section titled “start_driver”Initialize the browser or mobile driver session with JSON capabilities. Supports all drivers: Appium, Selenium, or Playwright.
Selenium and Playwright also support cookies parameter in capabilities that allows to set pre-defined cookies for authentication and headers parameter that allows to set custom headers for all browser requests.
For Playwright sessions, trace and videos are automatically recorded and saved to the artifacts directory.
stop_driver
Section titled “stop_driver”Stops running driver session and cleans up resources. Returns path to the artifacts directory, token usage statistics for the session and optionally saves the execution cache.
Perform actions in the application using natural language commands and return summary of the performed steps. Alumnium automatically captures screenshot upon completion and stores it in the artifacts directory.
Verify application state and run assertions using natural language commands. Returns the result of the check along with explanation the verification was evaluated. Alumnium automatically captures screenshot upon completion and stores it in the artifacts directory.
Extract data from the application based on natural language descriptions. If data is not found, returns explanation why it can’t be retrieved. Alumnium automatically captures screenshot upon completion and stores it in the artifacts directory.