PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

Chrome DevTools for Coding Agents: Official MCP Server for Browser Inspection & Automation

github.com | tool | #ai-security | #mcp | #devtools | #debugging | #coding-agents | #puppeteer | #chrome-devtools | #browser-automation
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

The official MCP server from Chrome DevTools lets AI coding agents like Claude and Cursor control and inspect live Chrome, with Puppeteer automation, performance tracing, and network analysis.

Why it matters

Bridges the gap between AI coding assistants and runtime browser environments, enabling agents to autonomously debug front-end errors, measure Core Web Vitals, and test web applications in real time.
Published
Collected

Related coverage

tool · github.com
Apple Private Cloud Compute (PCC) Security Source Code and Research Tools
Provides unprecedented source-level visibility into Apple's cloud AI infrastructure, allowing security researchers to verify cryptographic privacy guarantees and audit components eligible for Apple's PCC Security Bounty.
tool · github.com
Google ARTEMIS: Natural-Language Driven Android Automation & Mobile AI Agent Framework
Brings state-of-the-art vision-language agentic automation to Android mobile security, QA, and app testing, enabling autonomous vulnerability reproduction, exploratory stability testing, and seamless integration with AI developer toolchains via MCP.
tool · github.com
SpecterOps Skills: Open-Source LLM Agent Skills & MCP Plugin Marketplace for Red Teaming and AppSec
As AI-assisted offensive security evolves from simple prompting to multi-agent architectures, SpecterOps standardizes security craft into declarative skills and MCP interfaces, allowing operators to safely orchestrate complex red team tradecraft and reverse engineering directly through LLM agents.
tool · github.com
x64dbg-MCP Server: MCP-powered agentic reverse engineering for x64dbg
The project gives AI assistants a broad, scriptable interface to x64dbg for binary analysis and malware research. Because it can read and write debugged-process memory and execute debugger actions over HTTP, keep the server bound to trusted interfaces, retain bearer authentication, and avoid exposing its unencrypted endpoints to untrusted networks.
research · portswigger.net
Unearthing Z͌̈́̾a͊̈́l͊̿g̏̉͆o̾̚̚S̝̬ͅc̬r̯̼͇ͅi̼͖̜̭͔p̲̘̘̹͖t̠͖̟̹͓͇ͅ with visual fuzzing
Gareth Heyes uses visual fuzzing with headless Chrome and puppeteer to hunt Unicode combining characters that form render-defect Zalgo JavaScript, valid on Edge.
research · blog.quarkslab.com
Linux kernel instrumentation from Qemu and Gdb
A tutorial on instrumenting the Linux kernel from QEMU and GDB: using a hypervisor for stealthy analysis, plus GDB scripting and kernel helper tools to monitor syscalls, processes and modules.
Back