Browserless Docs MCP

Connect to Browserless documentation directly from your IDE or AI tool. This is a read-only documentation server. For browser automation capabilities via MCP, see the Browserless MCP Server.

Prerequisites

• An MCP-compatible IDE or AI tool (Cursor, Claude Desktop, VS Code, etc.)

Setup

Server URL: https://browserless-docs.mcp.kapa.ai

Setup steps vary depending on which AI assistant you're using.

Cursor

Add the following to your .cursor/mcp.json file:

{
  "mcpServers": {
    "browserless-docs": {
      "type": "http",
      "url": "https://browserless-docs.mcp.kapa.ai"
    }
  }
}

For more information, see the Cursor MCP documentation.

VS Code

Prerequisites: VS Code 1.102+ with GitHub Copilot enabled.

Create an mcp.json file in your workspace .vscode folder:

.vscode/mcp.json

{
  "servers": {
    "browserless-docs": {
      "type": "http",
      "url": "https://browserless-docs.mcp.kapa.ai"
    }
  }
}

For more details, see the VS Code MCP documentation.

Claude Code

Run the following command in your terminal:

claude mcp add browserless-docs https://browserless-docs.mcp.kapa.ai

For more information, see the Claude Code MCP documentation.

ChatGPT Desktop

If your ChatGPT Desktop build exposes remote MCP or custom connector support, you can use the same server URL:

1. Open ChatGPT Desktop.
2. Go to Settings > Features.
3. Enable Developer mode.
4. Navigate to Settings > MCP Servers.
5. Click Add Server and enter:
   • Name: browserless-docs
   • URL: https://browserless-docs.mcp.kapa.ai

For current setup guidance, see the OpenAI platform docs.

Claude Desktop

Add to your Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "browserless-docs": {
      "type": "http",
      "url": "https://browserless-docs.mcp.kapa.ai"
    }
  }
}

Restart Claude Desktop for changes to take effect.

For more details, see the Claude Desktop documentation.

Other

MCP is an open protocol supported by many clients. Use the server URL https://browserless-docs.mcp.kapa.ai and refer to your client's documentation for setup instructions.

Most clients accept the standard MCP JSON configuration format:

{
  "mcpServers": {
    "browserless-docs": {
      "url": "https://browserless-docs.mcp.kapa.ai"
    }
  }
}

What you can do

Once connected, you can ask context-aware questions about Browserless from within your editor. For example:

• "How do I connect to Browserless with Puppeteer?"
• "What are the available stealth options?"
• "How do I solve CAPTCHAs with BrowserQL?"

For a full overview of AI and agent integration options, see the AI & Agent Integrations guide. To get started with Browserless itself, check the Quickstart guide.

FAQ & Troubleshooting

How do I connect my agent to Browserless?

Pass your Browserless WebSocket URL (wss://production-sfo.browserless.io/chromium?token=YOUR_TOKEN) as the browser endpoint in your agent's configuration.

My agent is getting blocked by bot detection

Use the Browserless Agent instead of a plain Puppeteer/Playwright connection — it runs on Browserless's managed, stealth-enabled browser infrastructure with residential proxies built in, so most bot detection is handled without extra configuration.

Next steps

AI integrations overview

all supported AI frameworks and tools

BQL overview

use BrowserQL for advanced browser automation