WebRun Browser Automation for Claude Desktop
ai.webrun/webrun
Run multi-step tasks in a real Chrome browser: persistent environments, live view, human takeover.
client:Claude Desktop
transport:streamable-http
tools:21
Install WebRun Browser Automation in Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json · windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"webrun": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://api.webrun.ai/mcp"
]
}
}
}Claude Desktop has no remote transport in its config file, so this bridges through mcp-remote. Restart the app after saving. Claude Desktop docs
What Claude Desktop can do once it is connected
- browser_task
- create_session
- send_task
- pause_session_task
- resume_session_task
- stop_session_task
- terminate_session
- guardrail_response
- get_task_status
- screenshot
- list_sessions
- list_environments
- list_workflows
- get_workflow
- create_workflow
- update_workflow
- trigger_workflow
- create_agent
- list_agents
- pause_agent
- resume_agent