What is mcp-chrome-tabs CLAUDE.md?

Repository instructions for an MCP server, a program that lets an agent use external tools, to access browser tabs on macOS through AppleScript.

Use them when developing or maintaining the Chrome and Safari tab integrations, including unit tests, end-to-end tests, linting, and the MCP inspector.

They give contributors the commands and architecture needed to build, test, run, and inspect the server.

How pokutuna/mcp-chrome-tabs configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to pokutuna/mcp-chrome-tabs. 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/pokutuna/mcp-chrome-tabs/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/pokutuna/mcp-chrome-tabs

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/pokutuna/mcp-chrome-tabs/claude-md/github.svg)](https://agentmods.dev/instructions/pokutuna/mcp-chrome-tabs/claude-md)

Your own site

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

Per session 942 This file is loaded in full into every session.

When invoked 942 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	$0.00942	$0.00942
Opus 5.5	$0.00377	$0.00377
Sonnet 5.5	$0.00188	$0.00188
Haiku 4.5	$0.00094	$0.00094

Measured 1mo ago against content hash 41cf4bf21447, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-chrome-tabs 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 1mo 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 · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 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.

Development Commands

Building and Testing

npm run build - Compile TypeScript to JavaScript in dist/ directory
npm run test - Run unit tests with Vitest
npm test - Alias for npm run test
npm run test:watch - Run tests in watch mode
npm run test:e2e - Run end-to-end tests with Playwright

Development

npm run dev - Run the CLI directly from source using tsx
npm run start - Run the compiled version from dist/
npm run inspector - Open MCP inspector for debugging

Code Quality

npm run lint - Check code formatting with Prettier
npm run lint:fix - Fix code formatting issues

Architecture

This is an MCP (Model Context Protocol) server that provides access to browser tabs on macOS using JXA (JavaScript for Automation) over Apple Events.

Core Components

src/mcp.ts - Main MCP server implementation with tools and resources
src/browser/ - Browser-specific implementations
- browser.ts - Common browser interface and types
- chrome.ts - Chrome implementation
- safari.ts - Safari implementation (experimental)
- arc.ts - Arc implementation (experimental)
- osascript.ts - JXA execution utilities (timeout, retry, error hints)
src/view.ts - Content formatting and display utilities
src/util.ts - General utility functions
src/cli.ts - Command-line interface entry point
src/cli-options.ts - Command-line argument parsing

Key Features

The server provides three MCP tools:

list_tabs - List all browser tabs with IDs and metadata
read_tab_content - Extract readable content from tabs using Defuddle
open_in_new_tab - Open new URLs in browser

Resources:

tab://current - Active tab content
tab://{windowId}/{tabId} - Specific tab content

CLI commands (read-only, no MCP client needed):

list - List open tabs as [INDEX] ID TITLE DOMAIN, * marking the active tab
read <ID | INDEX | --active> - Read a tab's content

Read the full file on GitHub · 100 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.

1mo ago Changed · +13 lines · +237 tokens per session 41cf4bf21447
1mo ago Changed 647c2a9d59e7
2mo ago First seen · 87 lines · 705 tokens per session scan A 1c6dd12c93a0

Subscribe to this mod's changes

mcp-chrome-tabs CLAUDE.md is an instructions file published in the GitHub repository pokutuna/mcp-chrome-tabs (34 stars, last pushed 4d ago), licensed MIT. It adds 942 tokens to every session, about $0.0038 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 2026-08-30.

mcp-chrome-tabs CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-chrome-tabs CLAUDE.mdpokutuna/mcp-chrome-tabs	Instructions file	34	4d ago	MIT	A	942	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	yesterday	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

mcp-chrome-tabs: Instructions file for Claude Code