xfactor
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@xfactorshow me the latest console logs and network requests"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
xfactor
MCP server that connects AI agents to browser DevTools via CDP (Chrome DevTools Protocol).
Give your AI agent real-time access to browser console logs, network requests, and page state.
Features
Real-time console logs capture (errors, warnings, info, debug)
Network request/response monitoring
Page state (URL, title, viewport)
Works with any AI agent that supports MCP (Claude, etc.)
Related MCP server: chrome-dev-mcp
Quick Start
# Install dependencies
pnpm install
# Start the server (spawns Chrome + MCP server)
pnpm devConnect to your AI Agent
HTTP Mode (Recommended)
The server runs on http://localhost:3001 by default.
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"xfactor": {
"url": "http://localhost:3001/mcp"
}
}
}Other Agents
Point your MCP client to: http://localhost:3001/mcp
Available Tools
get_browser_context
Get browser state including console logs and network requests.
{
"includePageState": true,
"includeLogs": true,
"includeRequests": true
}Returns:
status- Connection status, CDP port, attached pagespageState- Current URL, title, viewportconsoleLogs- Array of captured console messagesnetworkRequests- Array of captured network requests
refresh_browser
Refresh the page to capture logs from page load.
{
"clearLogs": true
}Configuration
Environment Variables
CDP_PORT- Chrome DevTools Protocol port (default: 9222)TARGET_URL- URL to monitor (default: localhost:3000)
xmcp.config.ts
const config: XmcpConfig = {
http: { port: 3001 },
// ... other options
};How It Works
pnpm devspawns a Chrome instance with remote debugging enabledMCP server connects to Chrome via CDP
CDP listeners capture console logs and network activity
AI agents query the captured data via MCP tools
Requirements
Node.js >= 20
Google Chrome installed
pnpm
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Live browser debugging for AI assistants — DOM, console, network via MCP.
A paid remote MCP for AI agent browser DevTools MCP, built to return verdicts, receipts, usage logs,
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceMCP server for browser debugging, inspection, and verification that streams console logs, network errors, and user actions into AI coding assistants.65AGPL 3.0
- AlicenseAqualityAmaintenanceAn MCP server that connects AI agents to a running Chrome tab via the Chrome DevTools Protocol (CDP), enabling runtime debugging and page inspection.62469 npm1ISC
- -licenseNot gradedqualityNot gradedmaintenanceMCP server that connects AI agents to a real Chrome browser via a WebSocket extension bridge, enabling over 40 browser control tools without debug mode or profile isolation.-
- AlicenseBqualityAmaintenanceA lightweight 30KB MCP browser automation server that uses raw Chrome DevTools Protocol to enable AI agents to browse the web, take screenshots, interact with elements, and capture live page events like console logs and network requests.2625 npm15MIT