What is chrometools-mcp CLAUDE.md?

A project guide for an MCP server that automates Chrome through Puppeteer, a browser-control library. It supports browser sessions that stay open between commands so a person and an AI assistant can continue working in the same tabs.

Use it to automate Chrome across Windows, WSL, Linux, or macOS, keep tabs open between server calls, and run the project's tests and build commands.

It explains how to install, run, test, and develop the browser automation server without losing the current browser state between interactions.

How docentovich/chrometools-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to docentovich/chrometools-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/docentovich/chrometools-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/docentovich/chrometools-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/docentovich/chrometools-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/docentovich/chrometools-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/docentovich/chrometools-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/docentovich/chrometools-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/docentovich/chrometools-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/docentovich/chrometools-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,168 This file is loaded in full into every session.

When invoked 2,168 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02168	$0.02168
Opus 5.5	$0.00867	$0.00867
Sonnet 5.5	$0.00434	$0.00434
Haiku 4.5	$0.00217	$0.00217

Measured 2mo ago against content hash bc48000296e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chrometools-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 2mo ago.

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 · 311 lines

How it starts

The opening of the file, as written. The whole thing — 311 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

chrometools-mcp - MCP (Model Context Protocol) server for Chrome automation using Puppeteer.

Cross-platform MCP server (Windows/WSL, Linux, macOS) that provides Chrome browser automation capabilities.

Active Specs

Spec	Status	Progress
SEGM-537 QA Unblockers	NEEDS APPROVAL	progress
Novofon Blockers (iframe/session/P1)	CODE COMPLETE — needs live e2e	progress

Key Architecture Concept

Persistent Browser Sessions: Browser tabs remain open after command execution, allowing users to:

Prepare pages manually between AI iterations
Continue work from previous state
Interact with pages between MCP server calls

This enables iterative workflows where the user and AI collaborate within the same browser session.

Installation & Usage

Users install and run via npx (single command, no setup):

npx chrometools-mcp

This design makes installation automatic and simple for end users.

Development Commands

# Install dependencies
npm install

# Run tests
npm test

# Build
npm run build

# Development/testing
npm start
# or
node index.js

Technology Stack

Puppeteer: Chrome automation library
MCP SDK: @modelcontextprotocol/sdk for server implementation
Transport: stdio (standard for MCP servers)

Core Workflow

User runs npx chrometools-mcp (or adds to MCP config)
MCP server launches Puppeteer with headless: false
AI sends commands via MCP tools → Server executes in Chrome
Browser tabs stay open after execution
User can manually interact with pages
Next AI request continues from current browser state

Implementation Guidelines

Puppeteer Configuration

// Browser should persist between commands
const browser = await puppeteer.launch({
  headless: false,  // User needs to see and interact
  // Keep browser alive between MCP calls
});

Read the full file on GitHub · 311 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.

2mo ago First seen · 311 lines · 2,168 tokens per session scan A bc48000296e5

Subscribe to this mod's changes

chrometools-mcp CLAUDE.md is an instructions file published in the GitHub repository docentovich/chrometools-mcp (9 stars, last pushed 4mo ago), licensed ISC. It adds 2,168 tokens to every session, about $0.0087 per session on Opus 5.5. 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.

Browser automation

chrometools-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
chrometools-mcp CLAUDE.mddocentovich/chrometools-mcp	Instructions file	9	4mo ago	ISC	A	2,168	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	279k	today	MIT	A	4,325	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

chrometools-mcp: Instructions file for Claude Code