@webeyez/mcp-server

Webeyez Model Context Protocol (MCP) Server

Access Webeyez session replays, JavaScript errors, conversion funnels, and performance diagnostics directly from any MCP-compatible AI client.

What is Webeyez?

Webeyez is a comprehensive real-time user experience monitoring and diagnostic platform that helps online businesses detect, investigate, and resolve issues impacting their users. By tracking user friction, client-side errors, and drop-offs, Webeyez pinpoints exact conversion and revenue leaks.

All data, insights, and opportunities collected by Webeyez are available through the Model Context Protocol (MCP). This allows your AI agents and assistants to query live performance data, search session recordings, inspect JavaScript logs, and analyze conversion drop-offs directly within your chat environment.

This server implements the Model Context Protocol (MCP) to seamlessly expose Webeyez's core analytics tools into AI clients such as Claude (Web App), Claude Desktop, Cursor, Windsurf, Cline, and any other MCP-compliant interface.

Installation

npm install -g @webeyez/mcp-server

Connection Setup

The Webeyez MCP server supports both SSE (Server-Sent Events) for web applications and stdio/SSE bridging for local desktop editors.

Option 1: SSE Configuration (e.g., Claude Web App)

Register the server as a custom connector in web-based clients:

• Go to Settings > Connectors > Add custom connector (or equivalent in your AI client).
• Enter the connector URL: https://api.app.webeyez.com/mcp
• Log in with your Webeyez credentials when prompted.

Option 2: Stdio Bridge Configuration (e.g., Claude Desktop, Cursor, Windsurf)

Since local editor applications expect local processes, connect them to the remote server using the official mcp-remote bridge tool.

For Claude Desktop:

Configure your claude_desktop_config.json:

{
  "mcpServers": {
    "webeyez": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.app.webeyez.com/mcp"
      ]
    }
  }
}

For Cursor:

• Go to Settings > Features > MCP.
• Click + Add New MCP Server.
• Set Name to webeyez.
• Set Type to command.
• Set Command to:

  npx -y mcp-remote@latest https://api.app.webeyez.com/mcp
  

Available Tools

All tools require standard authentication (which is handled automatically via OAuth on connection setup):

Core AI Query Tools (Query live data using natural language)

• start_webeyez_query: Kicks off a long-running natural language query to the Webeyez AI agent regarding any data collected by Webeyez (including session replays, conversion funnels, JS errors, failed API calls, and revenue impact).
• check_webeyez_status: Polls and retrieves the status and the final response of a running background query.
• get_organizations_list: Lists all organizations the authenticated user has access to.
• get_organization_domains: Lists all registered domains under a specific organization.
• logout_webeyez: Safely logs out and resets saved connection context.

Direct Resource Tools (Direct query and management stubs)

• list_accounts: Lists accessible Webeyez accounts.
• list_sites: Lists configured sites.
• get_site_status: Returns tracking and integration status.
• get_revenue_loss_estimate: Returns estimated conversion and revenue losses.
• get_funnel_summary: Retrieves conversion funnel analysis.
• get_checkout_dropoffs: Returns checkout friction details.
• get_js_errors: Returns client-side JavaScript console errors.
• get_failed_api_calls: Lists failed HTTP network requests.
• get_session_examples: Retrieve recorded session replay links and examples.
• create_issue_export: Export detected issues and anomalies.
• connect_shopify_store / connect_magento_store: Platform integration shortcuts.
• manage_tracker_settings: Configures client tracker preferences.

License

ISC License