Skip to main content
Our Model Context Protocol (MCP) server lets any compatible AI model or agent launch Chromium browsers, execute Playwright code, capture video replays, and automate web interactions from Kernel’s cloud platform via a single secure endpoint.

Setup Instructions

General (Transports)

  • Streamable HTTP (recommended): https://mcp.onkernel.com/mcp
  • stdio via mcp-remote (for clients without remote MCP support): npx -y mcp-remote https://mcp.onkernel.com/mcp
Use the streamable HTTP endpoint where supported for increased reliability. If your client does not support remote MCP, use mcp-remote over stdio. Kernel’s server is a centrally hosted, authenticated remote MCP using OAuth 2.1 with dynamic client registration.

Authentication

The MCP server uses OAuth 2.1 for user authentication. When you connect through supported clients, you’ll be prompted to authorize access via your browser.

API Key Authentication

For programmatic access or service-to-service authentication, you can use your Kernel API key instead of OAuth. Add your API key to the MCP configuration:
The server automatically detects non-JWT tokens and treats them as API keys. API key authentication is useful for:
  • Automated workflows and CI/CD pipelines
  • Server-to-server integrations
  • Environments where OAuth flows are not practical
API keys bypass the OAuth flow but still require valid Kernel credentials. Ensure your API key is kept secure and not exposed in client-side code.

Connect in your client

Quick setup: Use the Kernel CLI to automatically configure MCP for your tool: kernel mcp install --target <target>. See the CLI MCP documentation for details.

Claude

Our remote MCP server is not compatible with the method Free users of Claude use to add MCP servers.

Pro, Max, Team & Enterprise (Claude.ai and Claude Desktop)

  1. Go to Settings → Connectors → Add custom connector.
  2. Enter: Integration name: Kernel, Integration URL: https://mcp.onkernel.com/mcp, then click Add.
  3. In Settings → Connectors, click Connect next to Kernel to launch OAuth and approve.
  4. In chat, click Search and tools and enable the Kernel tools if needed.
On Claude for Work (Team/Enterprise), only Primary Owners or Owners can enable custom connectors for the org. After it’s configured, each user still needs to go to Settings → Connectors and click Connect to authorize it for their account.

Claude Code CLI

Using Kernel CLI (recommended):
Manual setup:

Cursor

Using Kernel CLI (recommended):
One-click install: Click here to install Kernel on Cursor.

Manual setup

  1. Press ⌘/Ctrl Shift J.
  2. Go to MCP & Integrations → New MCP server.
  3. Add this configuration:
  1. Save. The server will appear in Tools.

OpenCode

Add the following to your ~/.config/opencode/opencode.jsonc:
Then authenticate using the OpenCode CLI:

Goose

Using Kernel CLI (recommended):
The command will display the YAML configuration to add to your Goose config file. One-click install: Click here to install Kernel on Goose in one click.

Goose Desktop

  1. Click Extensions in the sidebar of the Goose Desktop.
  2. Click Add custom extension.
  3. On the Add custom extension modal, enter:
    • Extension Name: Kernel
    • Type: STDIO
    • Description: Access Kernel's cloud-based browsers via MCP
    • Command: npx -y mcp-remote https://mcp.onkernel.com/mcp
    • Timeout: 300
  4. Click Save Changes button.

Goose CLI

  1. Run the following command:
  2. Select Add Extension from the menu.
  3. Choose Command-line Extension.
  4. Follow the prompts:
    • Extension name: Kernel
    • Command: npx -y mcp-remote https://mcp.onkernel.com/mcp
    • Timeout: 300
    • Description: Access Kernel's cloud-based browsers via MCP

Visual Studio Code

Using Kernel CLI (recommended):
Manual setup: Add to your VS Code settings.json:
Or use the UI:
  1. Press ⌘/Ctrl Shift P → search MCP: Add Server.
  2. Select HTTP (HTTP or Server-Sent Events).
  3. Enter: https://mcp.onkernel.com/mcp
  4. Name the server Kernel → Enter.

Windsurf

Using Kernel CLI (recommended):
Manual setup:
  1. Press ⌘/Ctrl , to open settings.
  2. Navigate Cascade → MCP servers → View raw config.
  3. Paste:
  1. On Manage MCPs, click Refresh to load Kernel MCP.

Zed

Using Kernel CLI (recommended):
Manual setup:
  1. Press ⌘/Ctrl , to open settings.
  2. Paste:

Smithery

You can connect directly to https://mcp.onkernel.com/mcp, or use Smithery as a proxy using its provided URL.
  • Use Smithery URL in any MCP client:
    1. Open Smithery: Kernel.
    2. Copy the URL from “Get connection URL”.
    3. Paste it into your MCP client’s “Add server” flow.
  • Use Kernel in Smithery’s Playground MCP client:
    1. Open Smithery Playground.
    2. Click “Add servers”, search for “Kernel”, and add it.
    3. Sign in and authorize Kernel when prompted.

Others

Many other MCP-capable tools accept:
  • Command: npx
  • Arguments: -y mcp-remote https://mcp.onkernel.com/mcp
Configure these values wherever the tool expects MCP server settings.

Tools

Each Kernel feature has a single manage_* tool with an action parameter, keeping the tool set small and consistent. Four standalone tools handle high-frequency workflows.

manage_* tools

  • manage_browsers - Create, list, get, and delete browser sessions. Supports headless/stealth modes, profiles, proxies, viewports, extensions, and SSH tunneling.
  • manage_profiles - Setup (with guided live browser session), list, and delete browser profiles for persisting cookies and logins.
  • manage_browser_pools - Create, list, get, delete, and flush pools of pre-warmed browsers. Acquire and release browsers from pools.
  • manage_proxies - Create, list, and delete proxy configurations (datacenter, ISP, residential, mobile, custom).
  • manage_extensions - List and delete uploaded browser extensions.
  • manage_apps - List apps, invoke actions, get/list deployments, and get invocation results.

Standalone tools

  • computer_action - Mouse, keyboard, and screenshot controls for browser sessions (click, type, press_key, scroll, move, get_position, screenshot).
  • execute_playwright_code - Execute Playwright/TypeScript code against a browser with automatic video replay and cleanup.
  • exec_command - Run shell commands inside a browser VM. Returns decoded stdout/stderr.
  • search_docs - Search Kernel platform documentation and guides.

Resources

  • browsers:// - Access browser sessions (list all or get specific session)
  • browser_pools:// - Access browser pools (list all or get specific pool)
  • profiles:// - Access browser profiles (list all or get specific profile)
  • apps:// - Access deployed apps (list all or get specific app)

Prompts

  • kernel-concepts - Get explanations of Kernel’s core concepts (browsers, apps, overview)
  • debug-browser-session - Get a comprehensive debugging guide for troubleshooting browser sessions (VM issues, network problems, Chrome errors)

Troubleshooting

  • Cursor clean reset: ⌘/Ctrl Shift P → run Cursor: Clear All MCP Tokens (resets all MCP servers and auth; re-enable Kernel and re-authenticate).
  • Clear saved auth and retry: rm -rf ~/.mcp-auth
  • Ensure a recent Node.js version when using npx mcp-remote
  • If behind strict networks, try stdio via mcp-remote, or explicitly set the transport your client supports

Examples

Invoke apps from anywhere

Execute Playwright code dynamically

Set up browser profiles for authentication

Debug a browser session

Attach the debug-browser-session prompt to your conversation first, then ask for help debugging.