mcp-browser: Skill for Claude Code

.claude/skills/browser-mcp-executar-e-operar/SKILL.md

browser-mcp-executar-e-operar is a skill for Claude Code from flpccabral/mcp-browser. It costs 152 tokens per session (4,115 once invoked), scanned B, original, MIT.

Operating instructions for a browser-control server that lets an agent use Chrome through Playwright or an existing Chrome debugging connection. Playwright is a tool for automating web browsers, while CDP is Chrome's debugging interface.

In plain words
What is it for?
Use them to set up, run, configure, connect, troubleshoot, or inspect the browser-mcp-server and its available browser tools.
Why use it?
They explain how to start the server, connect it to Chrome, choose an operating mode, and diagnose connection or runtime problems.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

This is flpccabral/mcp-browser's own configuration. It tells Claude Code how to work on mcp-browser itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-browser configures →

Reuse

Borrowing it

Nothing to install: this file belongs to flpccabral/mcp-browser. 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/flpccabral/mcp-browser/main/.claude/skills/browser-mcp-executar-e-operar/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/flpccabral/mcp-browser

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.

agentmods badge for browser-mcp-executar-e-operar

README.md
[![agentmods](https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-executar-e-operar.svg)](https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-executar-e-operar)
Your own site
<a href="https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-executar-e-operar"><img src="https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-executar-e-operar.svg" alt="Measured on agentmods" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,115 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00152 $0.04115
Opus 5 $0.00076 $0.02057
Sonnet 5 $0.00030 $0.00823
Haiku 4.5 $0.00015 $0.00411

Measured 7d ago against content hash 492924027781, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

browser-mcp-executar-e-operar scanned grade B with 1 finding 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 7d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

no arquivo com `chmod 0600` e loga `[WS-SERVER] Token gerado em ...`.
.claude/skills/browser-mcp-executar-e-operar/SKILL.md · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Executar e operar o browser-mcp-server

Runbook para subir e operar o sistema nos seus 3 modos, com a anatomia de cada comando e as convenções de saída. Tudo abaixo foi verificado contra o código em 2026-07-18.

Quando NÃO usar esta skill

Situação Skill correta
Setup do zero (venv, dependências, Playwright install) browser-mcp-build-e-ambiente
Catálogo completo de env vars e flags browser-mcp-config-e-flags
Algo não conecta / falha em runtime browser-mcp-playbook-de-depuracao
Por que existem 3 modos, trade-offs de arquitetura browser-mcp-contrato-de-arquitetura
Medir tráfego de rede / console da página browser-mcp-diagnosticos-e-ferramentas
Teoria dos substratos e semântica das tools browser-automacao-referencia
Catálogo/medição das 39 tools (dump_tools.py, contagem) browser-mcp-diagnosticos-e-ferramentas

Mapa dos 3 modos

Modo Browser controlado Como ativar Processo(s)
1. Playwright (padrão) Chromium lançado pelo servidor Nada — é o default ao subir o servidor python -m browser_mcp.server
2. CDP Chrome já aberto pelo usuário Tool browser_connect_to_existing Servidor MCP + Chrome com --remote-debugging-port
3. Extensão Chrome real do usuário (sessão, cookies) Tool browser_connect_to_extension Servidor MCP (ou WS standalone) + extensão instalada

O servidor MCP fala stdio com o client (Claude, Hermes etc.). O WebSocket na porta 8765 é um canal paralelo só para a extensão Chrome.


Modo 1 — Playwright (padrão)

Comando confiável

cd /caminho/do/repo/mcp_browser
.venv/bin/python -m browser_mcp.server

Console script browser-mcp-server (corrigido em 2026-07-18)

pyproject.toml:62 registra browser-mcp-server = "browser_mcp.server:main". Até 2026-07-18 isto estava quebrado: main era async def, então o entry point síncrono só criava uma coroutine e saía. Foi corrigido — hoje main é síncrona (server.py:84) e faz asyncio.run(_run_server()) (server.py:91). Tanto browser-mcp-server quanto python -m browser_mcp.server funcionam.

Read the full file on GitHub · 323 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. 7d ago First seen · 323 lines · 152 tokens per session scan B 492924027781

Subscribe to this mod's changes

browser-mcp-executar-e-operar is a skill published in the GitHub repository flpccabral/mcp-browser (0 stars, last pushed 1mo ago), licensed MIT. It adds 152 tokens to every session and 4,115 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

azure-messaging-webpubsub-java

Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.

microsoft/skills · 43 tokens

google-safe-browsing

Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…

davidondrej/skills · 105 tokens