# openbrowser-ai MCP server

AI browser automation. Write async Python to navigate, click, type, and extract data.

## Links
- Registry page: https://www.getdrio.com/mcp/me-openbrowser-openbrowser-ai
- Repository: https://github.com/billy-enrizky/openbrowser-ai.git

## Install
- Command: `uvx openbrowser-ai`
- Auth: Not captured

## Setup notes
- Package: Pypi openbrowser-ai v0.1.41
- Package argument: --mcp
- Environment variable: OPENBROWSER_HEADLESS (default true)
- Environment variable: OPENBROWSER_ALLOWED_DOMAINS
- Environment variable: OPENBROWSER_USER_DATA_DIR (default ~/.config/openbrowser/profiles/default)
- Environment variable: OPENBROWSER_STORAGE_STATE (default ~/.config/openbrowser/profiles/default/storage_state.json)
- Environment variable: OPENBROWSER_COMPACT_DESCRIPTION (default false)
- Environment variable: OPENBROWSER_MAX_OUTPUT (default 10000)
- Environment variable: ANONYMIZED_TELEMETRY (default true)

## Tools
Not captured

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: me.openbrowser
- Version: 0.1.41
- Runtime: Pypi
- Transports: STDIO
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: May 6, 2026
- Source: https://registry.modelcontextprotocol.io