trigger_workflow — WebRun Browser Automation MCP Tool
trigger_workflow
(trigger workflow) is one of 21 tools on the
WebRun Browser Automation
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call trigger_workflow from your client
- Claude Code WebRun Browser Automation trigger_workflow run in your project directory
- Claude Desktop WebRun Browser Automation trigger_workflow ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor WebRun Browser Automation trigger_workflow ~/.cursor/mcp.json
- VS Code WebRun Browser Automation trigger_workflow .vscode/mcp.json
- Zed WebRun Browser Automation trigger_workflow ~/.config/zed/settings.json
- Windsurf WebRun Browser Automation trigger_workflow ~/.codeium/windsurf/mcp_config.json
- Cline WebRun Browser Automation trigger_workflow ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI WebRun Browser Automation trigger_workflow ~/.gemini/settings.json
- Grok WebRun Browser Automation trigger_workflow .mcp.json (in your project root)
- ChatGPT WebRun Browser Automation trigger_workflow Settings → Connectors → Advanced → Developer mode
- Claude.ai WebRun Browser Automation trigger_workflow Settings → Connectors → Add custom connector
- LangChain WebRun Browser Automation trigger_workflow pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http webrun https://api.webrun.ai/mcpOther tools on this server
- 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
- create_agent
- list_agents
- pause_agent
- resume_agent
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.