​
Getting Started with Co-Browser MCP

This guide will help you set up Co-Browser MCP and empower your AI with secure access to web data and APIs.

​
Step 1: Create an Account

To begin using Co-Browser’s MCP server for your AI agents, you’ll first need to register for a developer account.

1

Visit the Developer Dashboard

Navigate to our Developer Dashboard to start the registration process.

2

Register a New Account

Create your developer account using secure passkey authentication.

3

Set Up Your Profile

Complete your profile information to gain full access to MCP capabilities.

​
Step 2: Obtain Your API Key

API keys are essential for authenticating your AI agent requests to our MCP server.

1

Access API Key Management

From your Developer Dashboard, navigate to the API Key section.

2

Generate a New API Key

Click “Generate New API Key” and provide a descriptive name for your key.

3

Select MCP Server

Choose which MCP server you want to use and add OAuth authentication to allow the MCP server to act on your behalf.

Never expose your API key in client-side code or public repositories.

​
Step 3: Implement MCP for Your AI Agent

There are two main ways to implement our MCP server for your AI agents: via Cursor or using our Python SDK.

​
Option A: Cursor Integration

Create an mcp.json file in the .cursor folder of your project with the following configuration:

{
  "mcpServers": {
    "browser-use-mcp-server": {
      "url": "https://api-gateway.cobrowser.xyz/mcp/browser/sse?api_key=YOUR_API_KEY"
    },
    "api-use-mcp-server": {
      "url": "https://api-gateway.cobrowser.xyz/mcp/api/sse?api_key=YOUR_API_KEY"
    }
  }
}

Replace YOUR_API_KEY with the API key you generated in Step 2. The file must be placed in the .cursor directory within your project.

​
Option B: Python SDK Implementation

For more advanced integrations with your AI systems, use our Python SDK:

import asyncio
import logging

from mcp import ClientSession
from mcp.client.sse import sse_client

logging.basicConfig(
    level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
)

async def main():
    async with sse_client(
        url="https://api-gateway.cobrowser.xyz/mcp/api/sse?api_key=YOUR_API_KEY",
    ) as streams:
        async with ClientSession(*streams) as session:
            await session.initialize()

            # List available tools
            tools = await session.list_tools()
            print(tools)

asyncio.run(main())

The Python SDK offers more programmatic control for integrating with our MCP server. Install it using pip install mcp-client.

​
Step 4: Enable Gmail Integration (Optional)

If you plan to use Email-Use for Gmail operations through your AI agent, you’ll need to authenticate with Google OAuth.

1

Navigate to Integrations

From your Developer Dashboard, go to the Integrations section.

2

Connect with Google

Click “Connect with Google” and follow the authentication prompts.

3

Grant Required Permissions

Approve the requested Gmail permissions to enable email operations.

​
Next Steps

Browser-Use

Learn about web browsing capabilities for your AI agents

Email-Use

Explore API integration options for your AI agents