Getting Started

Get started with Webfuse in minutes. This guide walks you through creating an Automation Space and configuring your AI agent with the MCP Server.

Automate your first Web Session

Sign in to Webfuse Studio and create an Automation Space. A Space is where you configure how your web sessions run — Apps, Extensions, access controls. A Session is a live web session running with that configuration. You can launch as many Sessions as you want from a single Space.

1. Create a Space

   1. Click the Automation tile to create a new Space.
   2. Provide a unique Space Slug for your URL.
   3. Click “Open Session” to start your first Session.

   The Automation App will be installed and open in the Session. This is where you’ll find the configuration values needed to connect your AI agent.

2. Configure your Agent

   Connect your MCP client to the Session MCP Server. Pick your client below for one-click setup, or see Connect your MCP Client for full instructions.

   VS Code
   Install in VS Code

   Or add manually to .vscode/mcp.json in your workspace, or to user settings:

   {
     "servers": {
       "webfuse-session": {
         "type": "http",
         "url": "https://session-mcp.HOSTNAME/mcp",
         "headers": {
           "Authorization": "Bearer ${input:webfuse_api_key}"
         }
       }
     },
     "inputs": [
       {
         "type": "promptString",
         "id": "webfuse_api_key",
         "description": "Webfuse Space REST API Key",
         "password": true
       }
     ]
   }

   Cursor
   

   Or add manually to .cursor/mcp.json:

   {
     "mcpServers": {
       "webfuse-session": {
         "type": "http",
         "url": "https://session-mcp.HOSTNAME/mcp",
         "headers": {
           "Authorization": "Bearer <your-space-rest-api-key>"
         }
       }
     }
   }

   Claude

   Add to claude_desktop_config.json:

   {
     "mcpServers": {
       "webfuse-session": {
         "type": "http",
         "url": "https://session-mcp.HOSTNAME/mcp",
         "headers": {
           "Authorization": "Bearer <your-space-rest-api-key>"
         }
       }
     }
   }

   Python SDK

   # To install the required library: pip install mcp
   
   import asyncio
   from mcp import ClientSession
   from mcp.client.streamable_http import streamablehttp_client
   
   async def main():
       async with streamablehttp_client(
           "https://session-mcp.HOSTNAME/mcp",
           headers={"Authorization": "Bearer <your-space-rest-api-key>"},
       ) as (read, write, _):
           async with ClientSession(read, write) as session:
               await session.initialize()
               result = await session.call_tool(
                   "see_domSnapshot", {"session_id": "<session-id>"}
               )
   
               print(result)
   
   if __name__ == "__main__":
       asyncio.run(main())

3. Try it out

   Once your Agent is configured and you have the Session ID ready. You can try it out with this sample prompt

   In the webfuse session with session id s52IbkuYxqolTzyFcPwGHoB23M1A,
   Navigate to dev.webfuse.com.

What’s next?

Now that your agent is connected, explore what Webfuse can do.

Explore available tools See the full list of MCP tools your agent can use to interact with web sessions.

Spaces & Sessions Learn how to configure Spaces and manage Sessions for your use case.

Extensions Augment any website with custom UI and logic using Extensions.

Integration Integrate Webfuse into your platform with widgets, APIs, and embedding options.