pulsemcp Safe content atomic mcp-remote

Chrome DevTools

This MCP server provides AI assistants with direct control over Chrome browsers through Chrome DevTools, enabling reliable web automation, debugging, and performance analysis using Puppeteer for browser control and Chrome DevTools for trace recording. Built by Google with TypeScript, it offers 26 tools across categories including input automation (clicking, filling forms, drag-and-drop), navigation (page management, history), network analysis (request inspection, throttling), performance tracing with Chrome DevTools insights, console debugging, and screenshot/snapshot capabilities. The implementation uses accessibility tree snapshots for reliable element targeting, automatically waits for page events after actions, supports CPU and network emulation for testing, and integrates Chrome's performance trace engine for actionable insights, making it valuable for automated testing workflows, web debugging, performance optimization, and building AI assistants that need to interact with live web applications through a real browser environment.

Cognium trust score

50%

Tier

Unverified

Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.

View full trust & usage report →

Metadata

Version: 1.0.0
Skill type: atomic
Execution layer: mcp-remote
Category: browser-automation
Source: PulseMCP
Repository: github.com/chromedevtools/chrome-devtools-mcp
Author type: human
Updated: 2026-05-27

View source Find related skills

MCP

Resolve Chrome DevTools from your agent

Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.

One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.

claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp

Swap --scope user for --scope project to commit it to .mcp.json.

Your client Same endpoint everywhere; only the config key differs. The full list is in the descriptor.

Claude Desktop · Settings → Connectors → Add custom connector

https://api.skillsregistry.net/mcp

Paste the URL as the connector endpoint. No authentication.

ChatGPT · Settings → Connectors → Create (developer mode) → MCP server URL

https://api.skillsregistry.net/mcp

Authentication: none. Works in chat and deep research — the server exposes the connector search and fetch tools.

Codex CLI · ~/.codex/config.toml

[mcp_servers.skillsregistry]
url = "https://api.skillsregistry.net/mcp"