chrome-devtools-mcp CLAUDE.md

Repository instructions for developing chrome-devtools-mcp, an MCP server that lets coding agents inspect and control a live Chrome browser. MCP is a standard way for an agent to use external tools.

In plain words
What is it for?
Installing dependencies, building and type-checking the server, running tests, formatting code, starting it, and generating documentation.
Why use it?
They give the agent the project’s commands and development rules, including how to build, check, format, test, and run the server.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/ctrlshiftbryan/chrome-devtools-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/ctrlShiftBryan/chrome-devtools-mcp
Per session 1,580 This file is loaded in full into every session.
When invoked 1,580 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01580 $0.01580
Opus 5 $0.00790 $0.00790
Sonnet 5 $0.00316 $0.00316
Haiku 4.5 $0.00158 $0.00158

Measured yesterday against content hash 0109de5fc077, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chrome-devtools-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

chrome-devtools-mcp is an MCP (Model Context Protocol) server that enables AI coding agents to control and inspect a live Chrome browser. It acts as a bridge between MCP clients (like Claude, Cursor, Copilot) and Chrome DevTools, exposing 27 tools across categories: input automation, navigation, emulation, performance, network, and debugging.

Build & Development Commands

# Install dependencies
npm ci

# Build (clean, compile TypeScript, post-build processing, rollup)
npm run build

# Type checking without emitting files
npm run typecheck

# Format code (ESLint + Prettier)
npm run format

# Check formatting without fixing
npm run check-format

# Start the MCP server
npm run start

# Start with debug logging
npm run start-debug

# Run all tests
npm test

# Run only tests marked with test.only
npm run test:only

# Run only tests without rebuilding first
npm run test:only:no-build

# Update test snapshots
npm run test:update-snapshots

# Generate tool reference documentation
npm run docs:generate

# Full docs generation (build + generate + format)
npm run docs

Testing

The project uses Node.js built-in test runner. Test files are in tests/ directory mirroring the src/ structure.

Run a single test file:

npm run build && node --require ./build/tests/setup.js --no-warnings=ExperimentalWarning --test-reporter spec --test-force-exit --test build/tests/path/to/file.test.js

Run specific test with test.only:

npm run test:only

Architecture

Entry Point Flow

  1. src/index.ts - Node version validation, imports main
  2. src/main.ts - Server setup, tool registration, stdio transport
  3. src/cli.ts - CLI argument parsing (yargs)
  4. src/browser.ts - Browser launch/connection via Puppeteer

Core Components

McpContext (src/McpContext.ts)

  • Central state management for browser sessions
  • Manages pages, snapshots, network/console collectors
  • Handles emulation states (CPU throttling, network conditions)
  • Provides methods for page selection, element lookup by UID, dialog handling
  • Implements timeout adjustments based on throttling multipliers

Read the full file on GitHub · 193 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 193 lines · 1,580 tokens per session scan A 0109de5fc077

Subscribe to this mod's changes

chrome-devtools-mcp CLAUDE.md is an instructions file published in the GitHub repository ctrlShiftBryan/chrome-devtools-mcp (3 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 1,580 tokens to every session, about $0.0079 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.